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

    Neuronpedia

    INDEX
    Explanations

    access or help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     astrology
    1.29
     Coleoptera
    1.25
     jiwa
    1.25
     maroon
    1.25
     tractors
    1.24
    nrow
    1.24
     primaryStage
    1.22
    rafish
    1.21
     میراتھن
    1.20
     jars
    1.19
    POSITIVE LOGITS
    al
    1.06
    oner
    1.05
    inser
    1.05
     ως
    0.98
    aux
    0.97
    ot
    0.95
    er
    0.90
    ссмо
    0.90
    اول
    0.90
    el
    0.89
    Act Density 0.002%

    No Known Activations