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

    Neuronpedia

    INDEX
    Explanations

    a followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onents
    1.06
    các
    0.97
     Defts
    0.96
     QSOs
    0.95
    ാ
    0.93
     Архивная
    0.93
    thedocs
    0.92
     ($_
    0.90
     (\<
    0.90
    ोक
    0.90
    POSITIVE LOGITS
     few
    2.06
     lot
    1.96
     bunch
    1.87
     variety
    1.75
     couple
    1.73
     plethora
    1.73
     handful
    1.61
     whopping
    1.58
     good
    1.56
     mixture
    1.55
    Act Density 0.215%

    No Known Activations