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

    Neuronpedia

    INDEX
    Explanations

    dark indigo, capable handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Где
    0.40
     terl
    0.40
    ᅡ
    0.38
     área
    0.36
    rylic
    0.35
    Where
    0.35
    зіно
    0.35
     tutta
    0.35
    鴨
    0.34
    baseURL
    0.34
    POSITIVE LOGITS
    ству
    0.44
     задания
    0.42
     দিয়েছিলেন
    0.41
     Rely
    0.40
    losti
    0.39
     இப்பட
    0.39
    ویت
    0.39
    ৗ
    0.39
     scaff
    0.38
     Vestone
    0.38
    Act Density 0.000%

    No Known Activations