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

    Neuronpedia

    INDEX
    Explanations

    goods set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stmt
    0.68
    primary
    0.66
    listing
    0.62
    major
    0.60
    indices
    0.60
    ща
    0.59
    segment
    0.59
    ffmpeg
    0.58
    "].
    0.57
    article
    0.57
    POSITIVE LOGITS
     Questi
    0.87
     Inggris
    0.85
     questa
    0.82
     Bahkan
    0.82
     Diese
    0.82
     Style
    0.80
     Good
    0.80
     ご
    0.80
     Untuk
    0.80
     Découvrez
    0.80
    Act Density 0.004%

    No Known Activations