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

    Neuronpedia

    INDEX
    Explanations

    accidental mishaps and unexpected outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     divisors
    0.40
     vogliono
    0.39
     formally
    0.39
     methodologies
    0.39
     empir
    0.38
     verwenden
    0.38
     효율
    0.37
     promouvoir
    0.37
     शोषण
    0.37
     существуют
    0.37
    POSITIVE LOGITS
     accidentally
    1.02
     accidental
    0.89
     случайно
    0.81
     accident
    0.79
     inadvertently
    0.77
     unintentionally
    0.77
     mishap
    0.74
     inadvert
    0.73
    accident
    0.73
     unintentional
    0.68
    Act Density 0.117%

    No Known Activations