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

    Neuronpedia

    INDEX
    Explanations

    themes related to testing, mandates, and regulations in various contexts

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

    academic or specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pool
    -0.27
    Mappings
    -0.27
    Pool
    -0.26
     frem
    -0.26
     its
    -0.26
    centralwidget
    -0.26
    {:
    -0.25
     phase
    -0.25
     comienzo
    -0.25
     Various
    -0.25
    POSITIVE LOGITS
    ⤹
    0.67
    ✭✭
    0.65
    ੝
    0.64
     Biôgrafia
    0.60
    :✨
    0.59
    httphttps
    0.58
    AsUp
    0.58
    évaluateur
    0.58
     bowiem
    0.58
     ""],
    0.57
    Act Density 0.222%

    No Known Activations