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

    Neuronpedia

    INDEX
    Explanations

    gain, gaining, gained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    1.36
    لي
    1.14
    ，
    1.04
    that
    0.99
    ។
    0.89
    。）
    0.88
    ка
    0.86
    kh
    0.86
    jährigen
    0.85
    ،
    0.84
    POSITIVE LOGITS
    m
    1.16
    e
    1.13
    u
    1.04
    o
    0.97
    ed
    0.95
    in
    0.91
    กิน
    0.89
    al
    0.89
    ม
    0.89
    น
    0.88
    Act Density 0.015%

    No Known Activations