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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate importance or significance in a context

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

    following "key" or "major."

    np_acts-logits-general · gemini-2.0-flash

    key X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.79
    nasium
    -0.70
    homonymie
    -0.68
    ьаж
    -0.62
     höchste
    -0.62
    CPtr
    -0.60
     resourceCulture
    -0.60
     perfeita
    -0.59
    Geografía
    -0.58
    djangoproject
    -0.58
    POSITIVE LOGITS
     players
    0.88
     player
    0.83
    players
    0.67
     spelers
    0.66
     features
    0.62
     feature
    0.60
    player
    0.59
     figures
    0.59
     ingredient
    0.59
     figure
    0.57
    Act Density 0.276%

    No Known Activations