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

    Neuronpedia

    INDEX
    Explanations

    online game characters/roles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    raid
    -0.07
    Law
    -0.07
    unning
    -0.06
     deficient
    -0.06
    liğe
    -0.06
    Cake
    -0.06
    -linux
    -0.06
    abilité
    -0.06
    Sock
    -0.06
     ／
    -0.06
    POSITIVE LOGITS
    cházet
    0.07
    ,))↵
    0.07
    "sync
    0.07
     �
    0.07
    .AddScoped
    0.06
    (blank
    0.06
    ได
    0.06
    査
    0.06
     PdfPCell
    0.06
    áků
    0.06
    Act Density 0.038%

    No Known Activations