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

    Neuronpedia

    INDEX
    Explanations

    Install

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     literature
    -0.07
     salope
    -0.07
     audition
    -0.06
    ຫ
    -0.06
     volupt
    -0.06
     Joseph
    -0.06
     Retrieve
    -0.06
    mouseout
    -0.06
     totalitarian
    -0.06
     Accident
    -0.06
    POSITIVE LOGITS
    梭
    0.07
    ESCO
    0.07
    敩
    0.07
    FB
    0.07
    一分
    0.07
    シェ
    0.07
     бер
    0.07
    SKTOP
    0.07
    _FACE
    0.07
    ומב
    0.07
    Act Density 0.010%

    No Known Activations