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

    Neuronpedia

    INDEX
    Explanations

    fractions/equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     melanch
    -0.07
     Adapt
    -0.06
     полот
    -0.06
     Liqu
    -0.06
     hroz
    -0.06
     recogn
    -0.06
     amore
    -0.06
    _colors
    -0.06
     alunos
    -0.06
     believers
    -0.06
    POSITIVE LOGITS
    ‌ک
    0.08
    '=
    0.08
    :');↵
    0.07
     DataSource
    0.07
     ");
↵
    0.07
    "];
↵
    0.06
    .SendMessage
    0.06
    :user
    0.06
     omap
    0.06
    BackgroundColor
    0.06
    Act Density 0.006%

    No Known Activations