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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    This neuron doesn’t respond to any tokens—it never activates for any text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    acro
    -0.07
     кад
    -0.07
    adu
    -0.06
     پنج
    -0.06
    _bullet
    -0.06
    क
    -0.06
     Atom
    -0.06
    ّم
    -0.06
    ضو
    -0.06
     recovering
    -0.06
    POSITIVE LOGITS
    _STMT
    0.07
     {{
    0.06
    164
    0.06
    ;');↵
    0.06
    !
    0.06
    .textView
    0.06
     Researchers
    0.06
    ResponseStatus
    0.06
    °С
    0.06
    |↵↵
    0.06
    Act Density 0.142%

    No Known Activations