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

    Neuronpedia

    INDEX
    Explanations

    API file extensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =zeros
    -0.07
    _responses
    -0.07
     Pays
    -0.07
     Goddess
    -0.07
    Women
    -0.06
    _isr
    -0.06
    爷爷
    -0.06
     cámara
    -0.06
     mujeres
    -0.06
     for
    -0.06
    POSITIVE LOGITS
    多媒体
    0.07
     Barth
    0.07
    CLEAR
    0.07
    افت
    0.06
    ort
    0.06
    alse
    0.06
    ,opt
    0.06
    ...)↵
    0.06
     carry
    0.06
     No
    0.06
    Act Density 0.022%

    No Known Activations