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

    Neuronpedia

    INDEX
    Explanations

    density and continuum concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     didn
    0.70
     doesn
    0.56
     demise
    0.54
     railroad
    0.53
    mens
    0.52
    ไม่
    0.52
     nyeri
    0.52
     isn
    0.52
    matic
    0.52
     avoidance
    0.52
    POSITIVE LOGITS
    ﹑
    0.66
     BasicContainer
    0.63
    od
    0.63
    точ
    0.62
     bactéri
    0.62
     prehr
    0.62
    ଷ୍
    0.61
    μα
    0.61
     قوات
    0.61
     máu
    0.60
    Act Density 0.032%

    No Known Activations