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

    Neuronpedia

    INDEX
    Explanations

    page numbering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Red
    -0.08
    compar
    -0.08
    .db
    -0.07
     Minute
    -0.07
    raska
    -0.07
    anym
    -0.07
     పరిస్థిత
    -0.07
    econom
    -0.07
    Occupation
    -0.07
     Occup
    -0.07
    POSITIVE LOGITS
     ঘোষ
    0.09
     counting
    0.09
     germ
    0.08
     fejl
    0.08
     preceding
    0.08
     header
    0.08
     numbering
    0.08
    قيقي
    0.08
    (header
    0.08
     cacao
    0.08
    Act Density 0.005%

    No Known Activations