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

    Neuronpedia

    INDEX
    Explanations

    choosing hosting providers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.45
    搭
    0.44
     două
    0.43
    けど
    0.43
     two
    0.42
     bid
    0.42
     dụng
    0.42
     заявление
    0.42
     бази
    0.41
    แต่
    0.41
    POSITIVE LOGITS
     참고
    0.45
     سننے
    0.44
     흰
    0.44
     செயல
    0.43
     유튜브
    0.43
    creet
    0.43
    quirrel
    0.42
    BERG
    0.41
     HTMLSc
    0.41
    マットレス
    0.41
    Act Density 0.003%

    No Known Activations