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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     P
    -0.07
    .nodes
    -0.07
     finalized
    -0.06
    Fonts
    -0.06
    using
    -0.06
     fraud
    -0.06
    ')"↵
    -0.06
    arming
    -0.06
    ()]↵
    -0.06
    actual
    -0.06
    POSITIVE LOGITS
     πραγμα
    0.07
    rightness
    0.07
    แฟ
    0.06
     BusinessException
    0.06
     فارسی
    0.06
     उपलब
    0.06
    에서의
    0.06
     возв
    0.06
     مغ
    0.06
    merce
    0.06
    Act Density 0.009%

    No Known Activations