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

    Neuronpedia

    INDEX
    Explanations

    achieving goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.72
    I
    0.65
    م
    0.60
    In
    0.60
    :
    0.59
    AN
    0.59
    ف
    0.59
    е
    0.58
    ק
    0.58
    а
    0.56
    POSITIVE LOGITS
     Ettha
    0.54
     tble
    0.51
     médias
    0.50
     piante
    0.49
    क्ष्म
    0.47
     croche
    0.47
     tiendas
    0.47
    ုပ်တို့
    0.46
     모습을
    0.46
     मंदिरों
    0.46
    Act Density 0.115%

    No Known Activations