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

    Neuronpedia

    INDEX
    Explanations

    types of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mulheres
    0.52
     Peut
    0.50
     spost
    0.50
     debes
    0.49
    ามารถ
    0.49
     contrô
    0.49
     квіт
    0.46
     procé
    0.46
     pouvez
    0.46
     montrer
    0.45
    POSITIVE LOGITS
    тивно
    0.44
    uclease
    0.43
     גם
    0.43
    另一个
    0.41
    ]])
    0.40
    ]=
    0.40
    েন
    0.39
    =("
    0.39
     भी
    0.39
     <=
    0.39
    Act Density 0.014%

    No Known Activations