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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical issues and solutions in programming or software

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

    Something is "working fine."

    np_acts-logits-general · gemini-2.0-flash

    appears or disappears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )—
    -0.67
    ].)
    -0.67
    illeurs
    -0.65
    )--
    -0.64
     nahilalakip
    -0.63
    ”—
    -0.62
    ).]
    -0.62
    %</
    -0.61
    ">//
    -0.61
    —”
    -0.61
    POSITIVE LOGITS
    Personendaten
    0.74
     nowadays
    0.73
     بيها
    0.72
    InjectAttribute
    0.70
     تضيفلها
    0.69
     planification
    0.67
    titleMargin
    0.63
     espac
    0.62
     equipments
    0.60
     convenable
    0.59
    Act Density 0.751%

    No Known Activations