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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     फस
    0.43
    ensely
    0.42
     envisioned
    0.40
    eiro
    0.40
    myt
    0.40
     Walmart
    0.40
    تالي
    0.40
     slimming
    0.40
    oran
    0.39
     showcases
    0.39
    POSITIVE LOGITS
     他
    0.45
     perhatian
    0.43
    ing
    0.43
     NSUTF
    0.41
     Fears
    0.39
    の一つ
    0.38
    付近
    0.37
     vua
    0.37
     tetahi
    0.37
    厸
    0.37
    Act Density 0.000%

    No Known Activations