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

    Neuronpedia

    INDEX
    Explanations

    descriptions or roles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _check
    -0.07
     вполне
    -0.07
    /mac
    -0.07
    nar
    -0.07
    朴
    -0.07
    قيد
    -0.07
     widgets
    -0.07
    .class
    -0.07
     lc
    -0.07
    符合
    -0.07
    POSITIVE LOGITS
    (xpath
    0.07
     każd
    0.07
    Número
    0.07
    Ք
    0.07
    Accessory
    0.07
     Mean
    0.06
     Hmm
    0.06
    uploader
    0.06
    该公司
    0.06
    -parts
    0.06
    Act Density 0.077%

    No Known Activations