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

    Neuronpedia

    INDEX
    Explanations

    preceded by punctuation or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    だろう
    0.46
    Capability
    0.45
    疽
    0.44
     использование
    0.42
    瓴
    0.42
    が増
    0.42
     கடுமையான
    0.42
    信する
    0.42
     مضر
    0.41
    未來
    0.41
    POSITIVE LOGITS
     tones
    0.50
     explains
    0.50
     commandments
    0.50
     rituals
    0.49
     instruments
    0.48
     histories
    0.47
     om
    0.46
     regul
    0.45
     understands
    0.44
     eigent
    0.44
    Act Density 0.001%

    No Known Activations