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

    Neuronpedia

    INDEX
    Explanations

    abstract qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ATORS
    0.75
    ACIONES
    0.72
    ékek
    0.71
    ちゃんの
    0.70
    GORITH
    0.69
    IVATE
    0.69
    uzioni
    0.66
    ANIES
    0.65
    ğiniz
    0.63
    டுகிறது
    0.63
    POSITIVE LOGITS
    ment
    0.81
    ic
    0.67
    ly
    0.63
    ive
    0.62
    ية
    0.61
    ן
    0.60
    ı
    0.60
    ۍ
    0.60
    ous
    0.59
    ity
    0.59
    Act Density 0.642%

    No Known Activations