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

    Neuronpedia

    INDEX
    Explanations

    modelis a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    禇
    0.53
     لهم
    0.52
    家里
    0.49
     Hager
    0.49
    руются
    0.49
    rą
    0.48
    reated
    0.47
     filhos
    0.47
    :["
    0.47
     who
    0.46
    POSITIVE LOGITS
     tracing
    0.49
    รางวัล
    0.48
    تن
    0.45
    ർട്ട
    0.44
     Arcadia
    0.43
     image
    0.43
    र्श
    0.43
    image
    0.42
     Harvest
    0.41
    images
    0.41
    Act Density 0.000%

    No Known Activations