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

    Neuronpedia

    INDEX
    Explanations

    specific scientific terms and research-related keywords

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

    [@ citation markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     among
    -0.40
    RotationOrder
    -0.36
     mutually
    -0.34
     jointly
    -0.34
     parmi
    -0.33
     brought
    -0.33
     серед
    -0.33
     teams
    -0.32
     three
    -0.32
     Intelli
    -0.30
    POSITIVE LOGITS
    dafx
    0.76
     يتيمه
    0.68
    Gambas
    0.67
    argout
    0.66
    帖最后由
    0.65
    MessageTagHelper
    0.65
    PreferredItem
    0.64
    extAlignment
    0.64
     Biôgrafia
    0.63
    EDEFAULT
    0.62
    Act Density 0.480%

    No Known Activations