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

    Neuronpedia

    INDEX
    Explanations

    contention, conflicts, alternative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Надо
    0.49
    illerie
    0.45
     безо
    0.44
     emptying
    0.43
    apine
    0.42
    ausal
    0.42
     Daher
    0.42
     Поэтому
    0.41
     স্থল
    0.39
     Nox
    0.39
    POSITIVE LOGITS
    ASSI
    0.47
    ഘടന
    0.46
    IMPLEMENT
    0.46
    VIEW
    0.46
    ای
    0.45
    FEATURE
    0.45
    ופ
    0.44
     değer
    0.44
    ൂ
    0.44
    ASS
    0.44
    Act Density 0.013%

    No Known Activations