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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "ex."

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

    Following "ex" prefix

    np_acts-logits-general · gemini-2.0-flash

    ex words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Autorizaciones
    -0.67
    SBATCH
    -0.66
    aarrggbb
    -0.64
     Тогда
    -0.59
    TagHelper
    -0.56
    ői
    -0.55
    honneur
    -0.55
    SceneManagement
    -0.50
    LEGGI
    -0.50
     ciment
    -0.50
    POSITIVE LOGITS
    chang
    0.53
    usiai
    0.52
    calibur
    0.51
    changing
    0.49
    haus
    0.49
    Personendaten
    0.48
     Mach
    0.48
     Ante
    0.48
    changes
    0.47
     Ex
    0.47
    Act Density 0.107%

    No Known Activations