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

    Neuronpedia

    INDEX
    Explanations

    email closings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    同时也
    0.49
     Grazie
    0.47
     ！
    0.45
    !</
    0.45
     Tako
    0.44
     👋
    0.44
    aikum
    0.42
     علیہ
    0.41
     Anche
    0.41
     Adem
    0.40
    POSITIVE LOGITS
    ।-
    0.45
     census
    0.42
     việc
    0.39
    *-
    0.39
    **,
    0.38
    ור
    0.37
    LEN
    0.36
    có
    0.36
    योग
    0.36
    *,
    0.36
    Act Density 0.038%

    No Known Activations