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

    Neuronpedia

    INDEX
    Explanations

    frequency, recall, format, €

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.54
     finance
    0.45
     Finance
    0.42
     tief
    0.41
    chandise
    0.41
     እስከ
    0.41
     bankrupt
    0.41
     broke
    0.41
    ت
    0.41
     Line
    0.41
    POSITIVE LOGITS
     `:`,
    0.45
    Asalamualaikum
    0.43
    ၷ
    0.42
    레스
    0.42
    ⛔
    0.42
     vacanam
    0.41
    ₂,
    0.41
    [multimodal]
    0.40
    鞣
    0.40
     정보
    0.39
    Act Density 0.002%

    No Known Activations