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

    Neuronpedia

    INDEX
    Explanations

    lieutenant followed by rank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    -3.33
    In
    -2.95
    u
    -2.88
    N
    -2.86
    an
    -2.86
    in
    -2.80
    2
    -2.61
    J
    -2.58
    er
    -2.55
    Q
    -2.55
    POSITIVE LOGITS
    蜮
    2.58
     '
    2.55
    🅃
    2.53
    🅣
    2.42
    芣
    2.38
    𓁹
    2.30
    颏
    2.22
    2.19
    圌
    2.17
    𝕿
    2.13
    Act Density 0.004%

    No Known Activations