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

    Neuronpedia

    INDEX
    Explanations

    number of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ewater
    0.41
     Wada
    0.40
     newcomers
    0.39
    atil
    0.39
    acara
    0.38
     newcomer
    0.37
    ancı
    0.36
     Brom
    0.35
     आयरन
    0.35
    TabData
    0.35
    POSITIVE LOGITS
    બંધ
    0.49
     crunch
    0.43
    ከር
    0.43
     телефо
    0.37
     (#
    0.37
    ત્મક
    0.37
    lijk
    0.37
    Calories
    0.37
    DownLatch
    0.37
    asper
    0.36
    Act Density 0.036%

    No Known Activations