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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vc
    -0.07
    .PrintWriter
    -0.07
    share
    -0.07
    樊
    -0.07
     fø
    -0.07
    .getConfig
    -0.06
    脖子
    -0.06
    无可
    -0.06
    .type
    -0.06
     lane
    -0.06
    POSITIVE LOGITS
     Termin
    0.07
    סקס
    0.07
    /z
    0.07
    quia
    0.07
    治疗
    0.07
     existing
    0.07
    ちなみ
    0.06
    Stick
    0.06
     Forms
    0.06
    üğü
    0.06
    Act Density 0.003%

    No Known Activations