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

    Neuronpedia

    INDEX
    Explanations

    themes of transformation and positive change amidst adversity

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

    finding positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fiable
    -0.34
     fiables
    -0.34
     portanto
    -0.33
     Helden
    -0.33
    пиона
    -0.33
    selben
    -0.32
     su
    -0.32
    ธอ
    -0.32
     fusca
    -0.31
     Grünen
    -0.31
    POSITIVE LOGITS
    expandindo
    0.58
    EDEFAULT
    0.57
    السكان
    0.56
    0.52
    Revenir
    0.50
    typeorm
    0.47
    évaluateur
    0.47
    turning
    0.46
     المعيارى
    0.46
    GHIJKLM
    0.45
    Act Density 0.045%

    No Known Activations