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

    Neuronpedia

    INDEX
    Explanations

    specific phrases and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wege
    0.54
     порядку
    0.49
     линей
    0.47
     Genève
    0.46
     диапа
    0.46
     нажа
    0.45
     IntelliJ
    0.45
    are
    0.45
     произво
    0.45
     или
    0.44
    POSITIVE LOGITS
    作る
    0.46
    шої
    0.45
     trabal
    0.42
     shadowy
    0.41
    飧
    0.41
    映画
    0.40
    ੲ
    0.40
    ษา
    0.40
     foil
    0.40
    setBadgeText
    0.40
    Act Density 0.000%

    No Known Activations