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

    Neuronpedia

    INDEX
    Explanations

    annoying, irritating, or obnoxious behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arccos
    0.45
     insecure
    0.44
     anxious
    0.43
     anguish
    0.42
    泣
    0.40
     vicious
    0.38
    मिस्ट्री
    0.37
     punishing
    0.37
     suppressant
    0.37
    äter
    0.37
    POSITIVE LOGITS
     irritating
    1.26
     annoying
    1.17
     irritate
    1.09
     раздра
    1.06
     annoy
    1.01
     irrit
    1.00
     annoyance
    0.96
     irritation
    0.91
    irrit
    0.87
     irritated
    0.82
    Act Density 0.025%

    No Known Activations