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

    Neuronpedia

    INDEX
    Explanations

    varied document excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    curity
    -0.07
    ific
    -0.07
     Dresses
    -0.06
    ceptions
    -0.06
     BOTTOM
    -0.06
    '^$',
    -0.06
    [top
    -0.06
     proposition
    -0.06
    $errors
    -0.06
    gd
    -0.06
    POSITIVE LOGITS
     서울
    0.06
    -member
    0.06
     tier
    0.06
     Lee
    0.06
    .='<
    0.06
    048
    0.06
    Checking
    0.06
     kterým
    0.06
     tatto
    0.06
     pře
    0.06
    Act Density 0.000%

    No Known Activations