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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations for media and entertainment entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াধিক
    1.77
    mun
    1.62
     eben
    1.55
    lı
    1.52
    nosti
    1.51
    inicio
    1.51
    mates
    1.49
    kao
    1.49
     fomentar
    1.49
    یه
    1.48
    POSITIVE LOGITS
    できるよう
    1.45
    ä
    1.45
    ST
    1.44
    து
    1.44
    деся
    1.41
    ES
    1.41
    unjung
    1.38
    ん
    1.34
    ール
    1.34
    д
    1.34
    Act Density 0.000%

    No Known Activations