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

    Neuronpedia

    INDEX
    Explanations

    temporary variables and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nextInt
    0.42
    nextDouble
    0.41
     fenomeni
    0.35
     Pap
    0.35
     Scandal
    0.35
    ুতি
    0.34
     psychosis
    0.34
     donation
    0.34
     scam
    0.34
    広
    0.33
    POSITIVE LOGITS
     nuevamente
    0.45
     again
    0.44
     scratch
    0.42
    TimeSeries
    0.41
    amma
    0.41
     다시
    0.40
     вновь
    0.40
    ":[{"
    0.39
     किंग्स
    0.39
     lại
    0.39
    Act Density 0.002%

    No Known Activations