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

    Neuronpedia

    INDEX
    Explanations

    guide followed by topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.66
    0.64
    el
    0.62
    าที
    0.56
    ান
    0.55
     código
    0.54
    m
    0.54
    h
    0.52
     )
    0.52
     {})
    0.52
    POSITIVE LOGITS
     برای
    0.75
     to
    0.69
    book
    0.66
    ົວ
    0.64
    yourself
    0.63
    ל
    0.63
    ំពោះ
    0.62
    不仅
    0.61
     billionaires
    0.60
     riches
    0.59
    Act Density 0.014%

    No Known Activations