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

    Neuronpedia

    INDEX
    Explanations

    extracting information about subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.91
    endus
    0.84
    ے
    0.84
    يند
    0.70
     inspire
    0.66
     Serialization
    0.65
    ou
    0.65
    ا
    0.64
    并
    0.64
    য়
    0.63
    POSITIVE LOGITS
     रुपये
    0.81
     hugely
    0.80
    BeerItem
    0.80
     lanz
    0.77
     sobr
    0.75
     үй
    0.75
     Ү
    0.75
     meal
    0.73
     тө
    0.73
     steep
    0.73
    Act Density 0.000%

    No Known Activations