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

    Neuronpedia

    INDEX
    Explanations

    published

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !("{}",
    -0.73
     виправивши
    -0.67
    )";
    -0.63
     ::=
    -0.63
     linkovi
    -0.61
    parsedMessage
    -0.61
    :+:
    -0.61
    EndTag
    -0.59
    cloths
    -0.59
    %)$
    -0.59
    POSITIVE LOGITS
     onAnimation
    0.60
     the
    0.59
     an
    0.57
     a
    0.50
     padx
    0.50
    JUDGE
    0.47
     congi
    0.46
    Xna
    0.45
     why
    0.45
    lexikon
    0.44
    Act Density 0.005%

    No Known Activations