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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sugar
    -0.07
    UILD
    -0.07
     celery
    -0.06
    _schema
    -0.06
    inery
    -0.06
    .ro
    -0.06
    -h
    -0.06
    ">';↵
    -0.06
    agas
    -0.06
     SUB
    -0.06
    POSITIVE LOGITS
     чер
    0.08
    ONGLONG
    0.07
     segregated
    0.07
     registros
    0.06
     �
    0.06
     jeopard
    0.06
    .firstname
    0.06
     Tick
    0.06
    TriState
    0.06
     mã
    0.06
    Act Density 0.006%

    No Known Activations