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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !');↵
    -0.07
    入选
    -0.07
     cost
    -0.07
    送来
    -0.07
     send
    -0.07
    んじゃないか
    -0.07
     bridge
    -0.07
     probability
    -0.07
    Annual
    -0.06
    Connect
    -0.06
    POSITIVE LOGITS
    单品
    0.08
    ハー
    0.08
    _ops
    0.07
    オスス
    0.07
    Ổ
    0.07
     accusation
    0.07
    .AttributeSet
    0.07
     혹
    0.07
     Calder
    0.07
    นำมา
    0.07
    Act Density 0.012%

    No Known Activations