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

    Neuronpedia

    INDEX
    Explanations

    customer support issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ܚ
    -0.09
    ар
    -0.07
    程
    -0.06
    lasses
    -0.06
    banks
    -0.06
     righteousness
    -0.06
    为一体的
    -0.06
    xCF
    -0.06
     ozone
    -0.06
     nets
    -0.06
    POSITIVE LOGITS
     dispersed
    0.08
    Period
    0.08
    ✕
    0.08
    .picture
    0.07
    _quiz
    0.07
    KS
    0.07
    KO
    0.07
     dramatic
    0.07
    مقال
    0.07
    赡
    0.07
    Act Density 0.235%

    No Known Activations