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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming terms.

    oai_token-act-pair · gemini-2.0-flash

    programming code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]();
    -0.45
    wiat
    -0.42
    impl
    -0.41
    fer
    -0.40
    待ち
    -0.40
    erweise
    -0.39
    zość
    -0.39
     initialState
    -0.39
    емость
    -0.38
    chalk
    -0.38
    POSITIVE LOGITS
     '\\;'
    0.68
    IndentedString
    0.65
     مرئيه
    0.65
    MethodManager
    0.64
    AddTagHelper
    0.63
     HasFactory
    0.61
    HasForeignKey
    0.60
    ArgsConstructor
    0.60
    ByVersion
    0.58
    клопе
    0.58
    Act Density 4.819%

    No Known Activations