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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arak
    -0.07
     contractual
    -0.07
    Counter
    -0.07
    orum
    -0.06
    íně
    -0.06
     useDispatch
    -0.06
    FileDialog
    -0.06
    .spark
    -0.06
     bean
    -0.06
    Throw
    -0.06
    POSITIVE LOGITS
    _ACTIVE
    0.07
     {
↵
↵
↵
    0.06
     düşün
    0.06
     대구
    0.06
    toDouble
    0.06
    كيب
    0.06
    ѓ
    0.06
     descriptors
    0.06
    ımıza
    0.06
     γυνα
    0.06
    Act Density 0.005%

    No Known Activations