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

    Neuronpedia

    INDEX
    Explanations

    data presenting numerical results or metrics related to health conditions or treatments

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

    Fractions. e.g., "x/y" or "x of y"

    np_acts-logits-general · gemini-2.0-flash

    proportions and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -1.01
     utafitiHapana
    -0.81
    Personensuche
    -0.78
     насељу
    -0.72
     متعلقه
    -0.71
     purpoſe
    -0.66
    StoryboardSegue
    -0.66
     myſelf
    -0.65
     Biôgrafia
    -0.65
    UserScript
    -0.63
    POSITIVE LOGITS
     out
    1.93
    out
    1.35
     outta
    1.16
     Out
    1.08
    Out
    1.04
     OUT
    1.01
     из
    1.00
     מתוך
    0.94
     among
    0.81
     uit
    0.78
    Act Density 0.493%

    No Known Activations