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

    Neuronpedia

    INDEX
    Explanations

    avoiding negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     недоста
    0.79
    prova
    0.74
     sağlam
    0.73
    ufficient
    0.72
     attentively
    0.69
    த்திற்காக
    0.68
     ചെയ്തി
    0.67
    に対し
    0.67
     boldly
    0.67
     henüz
    0.67
    POSITIVE LOGITS
     headaches
    2.13
     headache
    1.76
     hassles
    1.62
     unnecessary
    1.59
     hassle
    1.58
     unwanted
    1.54
     wasted
    1.53
     unpleasant
    1.51
     heartache
    1.47
     annoyance
    1.45
    Act Density 0.468%

    No Known Activations