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

    Neuronpedia

    INDEX
    Explanations

    eventual outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    閉じる
    -1.49
    ṓ
    -1.41
     demandes
    -1.40
    龛
    -1.38
     '../../../../
    -1.38
    ección
    -1.37
     эффект
    -1.36
     possibilités
    -1.34
     السياس
    -1.34
    选中
    -1.30
    POSITIVE LOGITS
     my
    2.19
     I
    2.16
     felt
    1.45
     était
    1.41
     probably
    1.40
    isierten
    1.37
    当时
    1.30
    cheinend
    1.29
     had
    1.28
     był
    1.26
    Act Density 0.008%

    No Known Activations