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

    Neuronpedia

    INDEX
    Explanations

    references to available space in various contexts

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

    space saving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terça
    -0.41
    ArrowToggle
    -0.38
    stylers
    -0.36
     خارجية
    -0.35
     uLocal
    -0.35
    cachor
    -0.34
    宵
    -0.33
     atrav
    -0.32
     Mérimée
    -0.32
     lying
    -0.32
    POSITIVE LOGITS
     space
    0.97
    Space
    0.93
     Space
    0.90
     SPACE
    0.85
    SPACE
    0.83
    space
    0.82
    ruimte
    0.77
     espacio
    0.77
    スペース
    0.74
     ruimte
    0.70
    Act Density 0.016%

    No Known Activations