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

    Neuronpedia

    INDEX
    Explanations

    ima

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—it remains inactive across all inputs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _REQ
    -0.07
     worldview
    -0.07
    payments
    -0.07
     ROC
    -0.07
    oscopic
    -0.06
     getLocation
    -0.06
    .Age
    -0.06
     jehož
    -0.06
    aise
    -0.06
    LastName
    -0.06
    POSITIVE LOGITS
     Blockly
    0.07
    ­tion
    0.07
    getDrawable
    0.07
    obar
    0.07
     Injectable
    0.06
     seasoned
    0.06
    "${
    0.06
     �
    0.06
     forging
    0.06
     scheduling
    0.06
    Act Density 0.002%

    No Known Activations