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

    Neuronpedia

    INDEX
    Explanations

    awareness of self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    켐
    0.47
    뉸
    0.47
    YT
    0.47
     órg
    0.46
     donna
    0.45
    مار
    0.45
    INY
    0.45
     дерев
    0.44
     negeri
    0.44
    KIA
    0.44
    POSITIVE LOGITS
    大概
    0.44
     तेजी
    0.43
    California
    0.43
    onin
    0.41
    ｛
    0.40
    ges
    0.40
     généralement
    0.39
    ঘু
    0.39
     maximizing
    0.39
     झू
    0.39
    Act Density 0.003%

    No Known Activations