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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loft
    -0.07
     vines
    -0.07
     jade
    -0.07
    Flash
    -0.07
     flushed
    -0.06
    attend
    -0.06
    cur
    -0.06
     thrill
    -0.06
     رق
    -0.06
     profile
    -0.06
    POSITIVE LOGITS
    .ImageIcon
    0.06
    ',↵↵
    0.06
    ");//
    0.06
    İng
    0.06
    %↵↵
    0.06
    Reviewer
    0.06
    ें,
    0.06
    eceğiz
    0.06
    >');↵↵
    0.06
     DERP
    0.05
    Act Density 0.002%

    No Known Activations