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

    Neuronpedia

    INDEX
    Explanations

    continuation or proceeding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    телям
    0.41
    aktion
    0.39
    خاذ
    0.38
     مثلث
    0.38
    četně
    0.36
    autas
    0.36
     bursting
    0.34
    WithPath
    0.34
    אַר
    0.34
     marais
    0.34
    POSITIVE LOGITS
     CONTINUE
    0.57
    continue
    0.55
    Continue
    0.54
     continue
    0.53
     продолжа
    0.52
     Continue
    0.52
     continues
    0.52
     continuar
    0.48
     продовжу
    0.48
     continua
    0.47
    Act Density 0.258%

    No Known Activations