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

    Neuronpedia

    INDEX
    Explanations

    references to data structures and their attributes, particularly in coding

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

    coordinates `xy` and `xyz`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    newtheorem
    -0.46
    (!__
    -0.45
     arşivlendi
    -0.44
    ✭✭
    -0.43
    MenuInflater
    -0.42
    /**
    -0.41
    OGND
    -0.41
    hyrchwyd
    -0.41
    AndEndTag
    -0.41
    存于互联网档案馆
    -0.40
    POSITIVE LOGITS
    HideFlags
    0.57
    цездатний
    0.47
     незавершена
    0.43
    apimachinery
    0.43
    estacks
    0.40
     saites
    0.40
    ziplin
    0.39
    PRESA
    0.38
     Maier
    0.37
    Diweddarwch
    0.37
    Act Density 0.018%

    No Known Activations