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

    Neuronpedia

    INDEX
    Explanations

    chronological order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.97
    h
    0.74
    }
    0.70
    v
    0.69
    com
    0.65
    ags
    0.64
    k
    0.63
    curr
    0.62
     embodies
    0.62
    bu
    0.61
    POSITIVE LOGITS
    라
    0.93
     thei
    0.75
    기
    0.72
     chronological
    0.68
    어
    0.66
    etically
    0.66
    他
    0.66
    ม
    0.65
     नहर
    0.63
    두
    0.63
    Act Density 0.002%

    No Known Activations