Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    self-taught individuals and their experiences learning musical instruments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on instructional “how to” constructs—i.e. the infinitive phrase “how to [verb]” indicating learning or instruction.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     serial
    -0.07
     governments
    -0.07
    .res
    -0.06
    US
    -0.06
    STACK
    -0.06
     evolution
    -0.06
     zombies
    -0.06
    us
    -0.06
    select
    -0.06
     JT
    -0.06
    POSITIVE LOGITS
    Orientation
    0.07
    Webpack
    0.07
    )))),
    0.07
    commend
    0.07
    	done
    0.06
    AxisAlignment
    0.06
    TableView
    0.06
    ihan
    0.06
     concerted
    0.06
    HasColumnName
    0.06
    Act Density 0.015%

    No Known Activations