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

    Neuronpedia

    INDEX
    Explanations

    close/exit

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of saving and exiting the text editor in setup instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ns
    -0.07
    ."]↵
    -0.07
    "])
    -0.06
    Rand
    -0.06
    >,
    -0.06
     )}↵
    -0.06
    chars
    -0.06
    -fields
    -0.06
     أب
    -0.06
    /examples
    -0.06
    POSITIVE LOGITS
    apple
    0.07
     civilian
    0.06
     synth
    0.06
    stroy
    0.06
     Keyboard
    0.06
     ambiente
    0.06
     sonst
    0.06
    _CB
    0.06
     doğrult
    0.06
     Coron
    0.06
    Act Density 0.007%

    No Known Activations