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

    Neuronpedia

    INDEX
    Explanations

    killer, Rise, Value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     новую
    0.48
     కేంద్ర
    0.46
    CENT
    0.45
    Chinese
    0.45
     новое
    0.45
    onRouteChange
    0.44
    Square
    0.44
     китай
    0.44
    ጳ
    0.44
    陶瓷
    0.43
    POSITIVE LOGITS
     craziness
    0.57
     keli
    0.55
     badass
    0.55
     ferocious
    0.54
     TMZ
    0.54
     spate
    0.54
     terrib
    0.54
     uphill
    0.54
     treino
    0.54
     walang
    0.53
    Act Density 0.000%

    No Known Activations