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

    Neuronpedia

    INDEX
    Explanations

    beginnings of words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anim
    -0.07
     pow
    -0.07
     engaging
    -0.07
    Stats
    -0.06
    ittance
    -0.06
     architects
    -0.06
     posted
    -0.06
     Dag
    -0.06
    обрет
    -0.06
    _RANK
    -0.06
    POSITIVE LOGITS
    .edge
    0.07
     {{--<
    0.07
    Dictionary
    0.07
    στα
    0.06
     ];↵↵
    0.06
     |--------------------------------------------------------------------------↵
    0.06
     RemoteException
    0.06
    .Connection
    0.06
     Cair
    0.06
    _choices
    0.06
    Act Density 0.000%

    No Known Activations