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

    Neuronpedia

    INDEX
    Explanations

    trigger

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ں
    -0.08
     به
    -0.07
    辋
    -0.07
    促进
    -0.07
     Carlson
    -0.07
     estrogen
    -0.07
    rances
    -0.07
     Leaves
    -0.07
     MaterialApp
    -0.07
    ��
    -0.06
    POSITIVE LOGITS
    .thread
    0.07
    _depth
    0.07
    明日
    0.07
    شرو
    0.07
    姗
    0.07
    getID
    0.06
     أمس
    0.06
     ситуация
    0.06
    _COMM
    0.06
     errorHandler
    0.06
    Act Density 0.030%

    No Known Activations