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

    Neuronpedia

    INDEX
    Explanations

    organization websites (.org)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     successful
    0.61
    ્યાર
    0.59
    Maine
    0.58
     பயன்படுத்தி
    0.58
     treasure
    0.57
    (-
    0.57
     муниципа
    0.57
     regel
    0.56
     개인
    0.56
     Till
    0.56
    POSITIVE LOGITS
     GAL
    0.96
     نبی
    0.94
    Gal
    0.93
    getFlight
    0.87
    Gall
    0.87
    Га
    0.83
    Airline
    0.81
    ఠ
    0.80
    airline
    0.80
    Glam
    0.80
    Act Density 0.001%

    No Known Activations