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

    Neuronpedia

    INDEX
    Explanations

    the [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৫
    2.05
    ৮
    1.96
    ৪
    1.95
    ка
    1.80
     Highness
    1.75
     tumors
    1.73
    ש
    1.73
     and
    1.64
    ized
    1.59
    吗
    1.57
    POSITIVE LOGITS
    َ
    1.83
    ut
    1.56
    sau
    1.49
    mbito
    1.48
    ,
    1.44
    fasterxml
    1.39
    kter
    1.39
    sack
    1.38
    ्स
    1.36
    ுள்ளனர்
    1.35
    Act Density 0.227%

    No Known Activations