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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sic
    -0.07
    .numpy
    -0.07
     auc
    -0.07
    Generating
    -0.07
     Serious
    -0.07
     xa
    -0.07
    aiser
    -0.06
    etwork
    -0.06
    Viol
    -0.06
     covered
    -0.06
    POSITIVE LOGITS
    ϙ
    0.08
    蚩
    0.07
    /value
    0.07
     фиг
    0.07
    overlay
    0.07
    _dimension
    0.06
    toLowerCase
    0.06
    yız
    0.06
    rif
    0.06
    铌
    0.06
    Act Density 0.033%

    No Known Activations