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

    Neuronpedia

    INDEX
    Explanations

    detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lawsuits
    -0.07
     UDP
    -0.07
    —
    -0.07
    犯
    -0.06
     Pics
    -0.06
    Fecha
    -0.06
     чер
    -0.06
    菌
    -0.06
     punct
    -0.06
     nose
    -0.06
    POSITIVE LOGITS
    Handlers
    0.06
    ΕΛ
    0.06
    (ع
    0.06
     Celebration
    0.06
    (dAtA
    0.06
     sahiptir
    0.06
    اعي
    0.06
    tight
    0.06
    _ti
    0.06
    �
    0.06
    Act Density 0.025%

    No Known Activations