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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지는
    1.02
    alanine
    0.99
    tgts
    0.93
    𝑻
    0.90
    어진
    0.86
    ка
    0.84
    𝓂
    0.84
    უნქ
    0.83
    크
    0.83
    𝓇
    0.82
    POSITIVE LOGITS
    at
    1.00
    e
    0.90
    ↵↵
    0.86
    ut
    0.83
     laat
    0.83
    ul
    0.82
    an
    0.82
    j
    0.82
    n
    0.80
    s
    0.80
    Act Density 0.049%

    No Known Activations