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

    Neuronpedia

    INDEX
    Explanations

    units of measurement, or descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    の発
    0.50
     assays
    0.49
    の内
    0.49
    ли
    0.48
    ك
    0.47
     sano
    0.47
     в
    0.46
     colo
    0.46
     lì
    0.46
     își
    0.46
    POSITIVE LOGITS
    ampunk
    0.45
     Gesamt
    0.44
    örungen
    0.43
    zeigen
    0.40
     আসিল
    0.40
    ormous
    0.40
    pexels
    0.39
    wert
    0.39
     அதிகரி
    0.39
     Tổng
    0.39
    Act Density 0.001%

    No Known Activations