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

    Neuronpedia

    INDEX
    Explanations

    wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ый
    0.81
     gigi
    0.77
     пу
    0.76
     cornea
    0.76
     alınan
    0.75
     zwar
    0.73
    अप्र
    0.71
    ти
    0.71
    رہ
    0.70
    その
    0.70
    POSITIVE LOGITS
    eight
    0.95
    ∗</
    0.86
    eer
    0.81
    tournament
    0.76
    笆
    0.76
    eine
    0.76
    pounds
    0.75
    ようになる
    0.74
     moverse
    0.74
    e
    0.73
    Act Density 0.003%

    No Known Activations