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

    Neuronpedia

    INDEX
    Explanations

    Emotions and feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     producto
    -0.06
    private
    -0.06
    коп
    -0.06
    meal
    -0.06
    lda
    -0.06
     Spend
    -0.06
    JD
    -0.06
     groove
    -0.06
     Verse
    -0.06
    答案
    -0.06
    POSITIVE LOGITS
    _;↵
    0.07
     منه
    0.07
     Mem
    0.06
    _Address
    0.06
    &C
    0.06
     yytype
    0.06
    ationale
    0.06
     cuerpo
    0.06
    };
↵
    0.06
     교
    0.06
    Act Density 0.006%

    No Known Activations