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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion or commentary on current issues

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

    predicting following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     difficulté
    -0.33
     démarche
    -0.32
    rę
    -0.32
     Helfer
    -0.31
     ocasião
    -0.31
     plads
    -0.29
     Fürsten
    -0.29
     pieles
    -0.29
     Grünen
    -0.29
     dificultades
    -0.29
    POSITIVE LOGITS
     betweenstory
    0.76
     okuyayım
    0.73
     defaultstate
    0.71
     الحره
    0.70
    ंदीखरीदारी
    0.66
    +#+
    0.66
    adaptiveStyles
    0.66
     Efq
    0.66
    WebServlet
    0.64
    saraba
    0.64
    Act Density 0.001%

    No Known Activations