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

    Neuronpedia

    INDEX
    Explanations

    .S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Calder
    -0.06
     tossing
    -0.06
    choice
    -0.06
     Austr
    -0.06
    (property
    -0.06
     تف
    -0.06
     override
    -0.06
     unlink
    -0.06
    724
    -0.06
    FontAwesome
    -0.06
    POSITIVE LOGITS
    .S
    0.09
    戏
    0.08
    _STS
    0.07
    跨
    0.07
    S
    0.06
    りの
    0.06
     sai
    0.06
    別
    0.06
    别
    0.06
     VS
    0.06
    Act Density 0.002%

    No Known Activations