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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to marking or highlighting items

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

    out areas, beside, tick, stricken, not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wantErr
    -0.30
    LayoutConstraint
    -0.27
     treat
    -0.27
    rawDesc
    -0.27
     inf
    -0.27
    Съ
    -0.27
     tes
    -0.27
     jo
    -0.27
     manip
    -0.27
     des
    -0.27
    POSITIVE LOGITS
    RenderAtEndOf
    0.70
     BorderSide
    0.66
    0.64
    istoitu
    0.60
     preocupes
    0.60
    
    0.59
    xase
    0.58
    exitRule
    0.57
     Италијани
    0.57
     surla
    0.57
    Act Density 0.296%

    No Known Activations