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

    Neuronpedia

    INDEX
    Explanations

    code blocks and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    âne
    0.40
     oti
    0.38
    jez
    0.38
    kot
    0.37
    ayya
    0.37
    awanda
    0.36
    ientos
    0.36
     temu
    0.36
     tropes
    0.35
     paraphernalia
    0.35
    POSITIVE LOGITS
     Př
    0.41
     US
    0.41
    FROM
    0.38
    浜
    0.37
    自
    0.35
    相比
    0.35
    PD
    0.35
    SE
    0.34
     WHICH
    0.34
     UN
    0.34
    Act Density 0.009%

    No Known Activations