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

    Neuronpedia

    INDEX
    Explanations

    the followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite

    the followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     The
    0.95
    The
    0.89
    an
    0.82
    ↵
    0.76
    et
    0.74
    f
    0.70
    he
    0.67
    nThe
    0.67
    b
    0.67
    k
    0.65
    POSITIVE LOGITS
     at
    0.59
     is
    0.59
     ت
    0.58
    О
    0.58
    َل
    0.56
    贺
    0.56
     र
    0.56
     paquete
    0.56
     ق
    0.55
     లేదు
    0.55
    Act Density 0.301%

    No Known Activations