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

    Neuronpedia

    INDEX
    Explanations

    configuration options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     א
    0.50
    Pero
    0.48
     MARKETING
    0.46
    Bài
    0.44
     라
    0.44
    ק
    0.44
     וא
    0.43
    ଝ
    0.43
     택
    0.43
     אחר
    0.42
    POSITIVE LOGITS
     maximum
    0.54
    allow
    0.52
    disable
    0.51
     width
    0.50
     maximale
    0.50
     парамет
    0.48
    verbose
    0.48
    设置
    0.48
    maximum
    0.47
    loglevel
    0.46
    Act Density 0.009%

    No Known Activations