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

    Neuronpedia

    INDEX
    Explanations

    word games and lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pu
    -0.07
    theme
    -0.06
     Don
    -0.06
    ком
    -0.06
    вид
    -0.06
    chester
    -0.06
     Kons
    -0.06
    ē
    -0.06
     Job
    -0.06
    ěti
    -0.06
    POSITIVE LOGITS
     frec
    0.07
     "");
↵
    0.07
    (prob
    0.07
     intox
    0.07
    ERVED
    0.07
     obscured
    0.06
     غذ
    0.06
    ヾ
    0.06
     entrev
    0.06
     kararı
    0.06
    Act Density 0.045%

    No Known Activations