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

    Neuronpedia

    INDEX
    Explanations

    digits 5 7

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Living
    0.71
     retreating
    0.67
    겁
    0.64
     living
    0.64
    URAL
    0.64
     des
    0.62
    كون
    0.61
    ural
    0.60
     LIVING
    0.59
    odhya
    0.59
    POSITIVE LOGITS
    𝟕
    0.80
     Pati
    0.79
     quilted
    0.76
    ឡ
    0.73
    hInstance
    0.72
    উত্তর
    0.70
    秏
    0.70
     ലഭ
    0.70
    ၇
    0.70
     dependences
    0.70
    Act Density 0.026%

    No Known Activations