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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Empire
    -0.07
     lives
    -0.07
    @example
    -0.07
     league
    -0.06
    semicolon
    -0.06
    "F
    -0.06
     freak
    -0.06
    _RSA
    -0.06
     Dialogue
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    alto
    0.06
    elerinde
    0.06
    ilit
    0.06
    _perc
    0.06
    ancy
    0.06
     وضعیت
    0.06
    сих
    0.06
    ://%
    0.06
    unkt
    0.06
    rollo
    0.06
    Act Density 0.022%

    No Known Activations