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

    Neuronpedia

    INDEX
    Explanations

    expand, confident, international, pricing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.03
     По
    0.85
     У
    0.78
     За
    0.77
     А
    0.76
     Х
    0.76
    К
    0.73
     Во
    0.73
     Հ
    0.73
     Я
    0.72
    POSITIVE LOGITS
    er
    1.02
    u
    0.98
    il
    0.92
    ิ
    0.88
    ే
    0.87
    стве
    0.80
    ె
    0.80
    i
    0.79
    بر
    0.77
    ية
    0.76
    Act Density 0.000%

    No Known Activations