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

    Neuronpedia

    INDEX
    Explanations

    Awards, accomplishments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peculiar
    -0.07
     independence
    -0.06
     pattern
    -0.06
    :max
    -0.06
     جام
    -0.06
     comentario
    -0.06
    zero
    -0.06
    void
    -0.06
     penis
    -0.06
    done
    -0.06
    POSITIVE LOGITS
     velmi
    0.07
    .INTEGER
    0.07
     فو
    0.07
     перс
    0.06
     вихов
    0.06
    waukee
    0.06
    eee
    0.06
    eguard
    0.06
    _EXPR
    0.06
    戒
    0.06
    Act Density 0.015%

    No Known Activations