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

    Neuronpedia

    INDEX
    Explanations

    history/geography texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abbr
    -0.07
     planners
    -0.07
     Ber
    -0.06
     onClick
    -0.06
     throughout
    -0.06
    roke
    -0.06
     Armen
    -0.06
     row
    -0.06
    round
    -0.06
    .Token
    -0.06
    POSITIVE LOGITS
    [float
    0.07
     FILTER
    0.06
     Sole
    0.06
     Healing
    0.06
     Narendra
    0.06
    tainment
    0.06
    จะต
    0.06
     ecstasy
    0.06
     prospective
    0.06
    .website
    0.06
    Act Density 0.008%

    No Known Activations