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

    Neuronpedia

    INDEX
    Explanations

    newline character

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蘊
    0.33
    (
    0.32
    問題
    0.30
    周围
    0.29
     depolar
    0.29
     fokus
    0.29
    為
    0.29
     BER
    0.29
    蜂
    0.29
    ალური
    0.28
    POSITIVE LOGITS
    r
    0.54
    u
    0.47
    n
    0.45
    th
    0.41
    rt
    0.40
    ne
    0.39
    text
    0.39
    nThe
    0.38
    ing
    0.37
    ufe
    0.36
    Act Density 0.014%

    No Known Activations