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

    Neuronpedia

    INDEX
    Explanations

    Or, if, want, first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ج
    0.80
    נו
    0.75
    غ
    0.74
    ม
    0.73
    व
    0.71
    नई
    0.70
    }{
    0.69
    д
    0.69
    का
    0.68
    ल
    0.67
    POSITIVE LOGITS
     orchid
    0.93
     somatic
    0.87
    ives
    0.86
    INESS
    0.79
     orchids
    0.79
     saffron
    0.78
    烁
    0.78
     Rene
    0.77
     collage
    0.76
     exon
    0.76
    Act Density 0.002%

    No Known Activations