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

    Neuronpedia

    INDEX
    Explanations

    person

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _yaml
    -0.07
     tộc
    -0.07
    .Label
    -0.07
    .tsv
    -0.07
    zap
    -0.06
    QDebug
    -0.06
     thật
    -0.06
     lâu
    -0.06
    escription
    -0.06
     Jade
    -0.06
    POSITIVE LOGITS
     CPUs
    0.08
    суж
    0.07
     inning
    0.07
     Needless
    0.07
    بني
    0.06
     reunion
    0.06
     ceiling
    0.06
    怪物
    0.06
    epochs
    0.06
    станавли
    0.06
    Act Density 0.004%

    No Known Activations