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

    Neuronpedia

    INDEX
    Explanations

    curve

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coal
    -0.08
    等候
    -0.08
     Blood
    -0.07
    }elseif
    -0.07
     cnt
    -0.07
     infant
    -0.07
    agnostic
    -0.07
     classification
    -0.07
    Tap
    -0.07
    思念
    -0.07
    POSITIVE LOGITS
    中文
    0.08
    不舒服
    0.08
     gương
    0.07
    娵
    0.07
    лу
    0.07
    _slider
    0.07
     الاجتماعي
    0.07
     Pune
    0.07
    ﾛ
    0.07
    career
    0.07
    Act Density 0.006%

    No Known Activations