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

    Neuronpedia

    INDEX
    Explanations

    Railroad tracks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discouraged
    -0.07
    工夫
    -0.07
    %E
    -0.07
    是
    -0.07
     связан
    -0.06
    اختلاف
    -0.06
    贯通
    -0.06
     Specific
    -0.06
     battle
    -0.06
    ፤
    -0.06
    POSITIVE LOGITS
     fname
    0.09
     synthesis
    0.07
    hea
    0.07
    _FAMILY
    0.07
    匙
    0.07
    花瓣
    0.07
    osto
    0.07
    pra
    0.07
    レビュー
    0.07
    𝑘
    0.07
    Act Density 0.009%

    No Known Activations