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

    Neuronpedia

    INDEX
    Explanations

    assuming hypothetical conditions or ASIL levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    optical
    0.41
     deftly
    0.41
    败
    0.38
     intravenously
    0.38
    रण
    0.38
    Optical
    0.38
     epoxy
    0.37
    StateHandler
    0.37
    ឥ
    0.36
     betray
    0.36
    POSITIVE LOGITS
     এলা
    0.40
     डॉल
    0.39
     Booking
    0.38
    naz
    0.37
    anym
    0.37
     roaming
    0.37
     چک
    0.37
     Schreiben
    0.37
     Checklist
    0.37
     Abgerufen
    0.36
    Act Density 0.002%

    No Known Activations