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

    Neuronpedia

    INDEX
    Explanations

    references to different types of storage or hidden spaces, particularly in buildings

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

    building levels and spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bond
    -0.44
     Lyons
    -0.42
     succ
    -0.42
    ########.
    -0.41
     Monfieur
    -0.40
     MIP
    -0.40
     Barak
    -0.40
     فريبيس
    -0.40
    кну
    -0.39
    empio
    -0.39
    POSITIVE LOGITS
     attic
    0.71
     Attic
    0.53
    UnusedPrivate
    0.50
     énergé
    0.48
    adpleegd
    0.47
     nahilalakip
    0.45
    uxxxx
    0.44
     tartalomajánló
    0.43
    دانشنامهٔ
    0.43
    sidemargin
    0.42
    Act Density 0.003%

    No Known Activations