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

    Neuronpedia

    INDEX
    Explanations

    multilingual concepts and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Согласно
    0.56
    aria
    0.47
    aton
    0.47
     согласно
    0.47
     Squash
    0.46
    isi
    0.46
    itely
    0.46
    isely
    0.46
    iton
    0.45
     වැඩ
    0.44
    POSITIVE LOGITS
    賚
    0.47
    ิน
    0.44
    ла
    0.44
    стите
    0.44
    朗
    0.44
    驁
    0.43
    Rang
    0.42
    ED
    0.41
    想想
    0.41
    N
    0.40
    Act Density 0.002%

    No Known Activations