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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _we
    -0.07
     immigr
    -0.07
     Executive
    -0.07
     إليه
    -0.07
     إ
    -0.07
    龢
    -0.07
    ȅ
    -0.06
     Worse
    -0.06
    (New
    -0.06
    CompanyId
    -0.06
    POSITIVE LOGITS
    QN
    0.08
    百分
    0.07
    zilla
    0.07
     Rodrig
    0.07
    前锋
    0.07
     tails
    0.07
    煌
    0.07
    Skeleton
    0.07
    '](
    0.06
     sphere
    0.06
    Act Density 0.006%

    No Known Activations