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

    Neuronpedia

    INDEX
    Explanations

    for any

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    晟
    0.65
    泺
    0.63
    Spo
    0.63
     पदों
    0.63
     pastas
    0.62
     Schedules
    0.62
     图
    0.62
    मेर
    0.61
    rieden
    0.61
     Let
    0.60
    POSITIVE LOGITS
     camaraderie
    0.80
     madame
    0.75
     heterogeneity
    0.73
    ক্ষেপ
    0.72
     glande
    0.71
     deviant
    0.71
     réalité
    0.71
     brutality
    0.70
    ,(((
    0.70
     ulteriori
    0.70
    Act Density 0.008%

    No Known Activations