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

    Neuronpedia

    INDEX
    Explanations

    indicating comparison or continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    0.72
    C
    0.70
    y
    0.69
    s
    0.66
    o
    0.60
    all
    0.59
    and
    0.55
    ill
    0.55
    it
    0.54
    per
    0.53
    POSITIVE LOGITS
    。
    0.78
    。,
    0.66
    。"
    0.65
    ０
    0.61
    )。
    0.61
    。",
    0.60
    。</
    0.60
    。「
    0.59
    "。
    0.58
    聁
    0.58
    Act Density 0.000%

    No Known Activations