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

    Neuronpedia

    INDEX
    Explanations

    Elliott

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    323
    -0.07
    फ
    -0.07
    <ArrayList
    -0.07
    ergarten
    -0.06
     prostituer
    -0.06
    	Dictionary
    -0.06
    нике
    -0.06
    _contains
    -0.06
     دانشگاه
    -0.06
    字符串
    -0.06
    POSITIVE LOGITS
     zev
    0.08
     Lewis
    0.07
    acağ
    0.07
    heed
    0.07
    /apps
    0.06
     πρω
    0.06
     reap
    0.06
     Seventh
    0.06
     schw
    0.06
    Lewis
    0.06
    Act Density 0.033%

    No Known Activations