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

    Neuronpedia

    INDEX
    Explanations

    increment and decrement operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    एम
    1.07
    А
    1.05
    ными
    1.01
    ťaž
    0.95
    ంత
    0.94
    कत
    0.93
    ным
    0.93
    ssä
    0.91
    led
    0.90
    ót
    0.88
    POSITIVE LOGITS
     rearview
    1.23
    はこの
    1.08
     SNMP
    1.07
    はどう
    1.03
    "})
    1.02
     त्योहार
    1.02
    ्लाई
    1.02
    CapsLock
    1.02
     traced
    0.99
    は約
    0.98
    Act Density 0.010%

    No Known Activations