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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating moments of observation or transient experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quick looks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.49
     nonatomic
    -0.43
     télévisée
    -0.42
     Lengkap
    -0.41
     spowod
    -0.41
    utuhkan
    -0.40
     Komunikasi
    -0.40
    locaust
    -0.40
     dniu
    -0.39
     łóż
    -0.37
    POSITIVE LOGITS
     glimpse
    0.85
     glimp
    0.84
     briefly
    0.75
     glimpses
    0.73
     touched
    0.66
     brief
    0.64
     fleeting
    0.63
     touch
    0.63
     touches
    0.63
     touching
    0.60
    Act Density 0.039%

    No Known Activations