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

    Neuronpedia

    INDEX
    Explanations

    making recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.59
    \
    0.54
    ะ
    0.49
    '
    0.47
    .
    0.45
    可见
    0.44
     tequila
    0.43
    ์
    0.43
     ความ
    0.43
     receptor
    0.43
    POSITIVE LOGITS
    recommend
    0.80
    recommended
    0.79
    i
    0.76
    et
    0.70
     توصیه
    0.66
     recomend
    0.66
    recomend
    0.65
    r
    0.65
    ва
    0.64
     पद्धतीने
    0.63
    Act Density 0.056%

    No Known Activations