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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.54
    dır
    1.49
     allá
    1.46
    Ẳ
    1.34
    ólito
    1.33
    yed
    1.31
     enfim
    1.29
    giveness
    1.29
    yah
    1.28
    پلز
    1.28
    POSITIVE LOGITS
    ).
    1.63
    ),
    1.63
    ，
    1.55
    )
    1.52
    。
    1.48
    ،
    1.47
    .
    1.40
    )،
    1.38
    ")
    1.33
    ্লিকেশন
    1.27
    Act Density 0.151%

    No Known Activations