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

    Neuronpedia

    INDEX
    Explanations

    mathematical proof and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    スマート
    0.46
     можли
    0.45
    getDefaultSh
    0.43
    tobago
    0.43
     зовніш
    0.42
    Respiratory
    0.42
    вання
    0.42
    Seasonal
    0.42
     easiest
    0.41
     забезпечення
    0.40
    POSITIVE LOGITS
     yêu
    0.42
     阿
    0.40
     !
    0.40
     Oh
    0.39
     murderer
    0.39
     يرد
    0.39
    ষধ
    0.39
     mill
    0.38
     phi
    0.38
    អ
    0.38
    Act Density 0.000%

    No Known Activations