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

    Neuronpedia

    INDEX
    Explanations

    difficulty, time, budget, effort, friendly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    0.66
    。
    0.65
    朮
    0.61
     composés
    0.59
    you
    0.55
     pertanian
    0.55
    YOU
    0.54
     appliquée
    0.54
    ным
    0.53
    Você
    0.53
    POSITIVE LOGITS
    s
    0.79
    :
    0.71
     is
    0.70
    ни
    0.70
     are
    0.68
    ik
    0.65
     has
    0.65
    er
    0.63
    ing
    0.63
    es
    0.63
    Act Density 0.269%

    No Known Activations