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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formulas

    oai_token-act-pair · gemini-2.0-flash

    rm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.75
    ソッド
    -0.54
    ütfen
    -0.51
    Bilan
    -0.49
    ModelAdmin
    -0.47
     quoi
    -0.47
    клопе
    -0.47
    AssignableFrom
    -0.46
    Πηγή
    -0.46
    ighed
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.63
     виправивши
    0.60
    DockStyle
    0.55
    slidesPer
    0.52
     utafitiHapana
    0.52
    Gön
    0.51
    jins
    0.51
    KommentareTeilen
    0.51
    hlor
    0.50
     ujednoznacz
    0.50
    Act Density 3.537%

    No Known Activations