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

    Neuronpedia

    INDEX
    Explanations

    Attack and Damage Rolls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟹
    0.41
    檎
    0.41
     fir
    0.40
     SLASH
    0.39
     জ্ঞান
    0.39
    yyyy
    0.39
    യാ
    0.38
    ฉ
    0.38
     TextArea
    0.38
    コーヒー
    0.37
    POSITIVE LOGITS
     UK
    0.98
    United
    0.84
     United
    0.82
     Uk
    0.82
    UK
    0.81
     uk
    0.79
    Uk
    0.77
     यूनाइटेड
    0.75
    UNITED
    0.70
    uk
    0.66
    Act Density 0.000%

    No Known Activations