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

    Neuronpedia

    INDEX
    Explanations

    punctuations and sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     novas
    0.50
     neue
    0.48
     neuen
    0.47
     prots
    0.47
     idé
    0.47
     refugee
    0.46
     dienst
    0.46
     exs
    0.46
     Vedas
    0.46
     vaste
    0.45
    POSITIVE LOGITS
     由于
    0.48
    afficher
    0.47
     因为
    0.46
    药
    0.43
    Jx
    0.43
    我不
    0.42
     ngọt
    0.42
    因为
    0.41
    ㎏
    0.41
     删除
    0.41
    Act Density 0.014%

    No Known Activations