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

    Neuronpedia

    INDEX
    Explanations

    Does it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    1.11
    ↵
    0.94
    ことも
    0.86
    ».
    0.83
    こう
    0.80
     тоже
    0.78
    …。
    0.77
    —
    0.71
    ilerinin
    0.71
    Вот
    0.69
    POSITIVE LOGITS
    oretically
    1.49
    orems
    1.22
    로운
    1.08
    atrical
    1.05
     থাকুন
    1.04
     น
    1.04
     wird
    1.04
     émotion
    1.04
     বা
    1.03
    ેચ્છ
    1.02
    Act Density 1.273%

    No Known Activations