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

    Neuronpedia

    INDEX
    Explanations

    references to various rooms and spaces within a house

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

    rooms and spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.86
     Савезне
    -0.67
    Vidite
    -0.63
     Biôgrafia
    -0.62
    utilisons
    -0.60
    WireFormatLite
    -0.60
     fevere
    -0.59
     Reſ
    -0.57
    WTO
    -0.57
    MCI
    -0.56
    POSITIVE LOGITS
     rotina
    0.40
     badkamer
    0.31
     dormitorios
    0.31
     affari
    0.28
     baterai
    0.28
     czeka
    0.28
     ekor
    0.28
    jména
    0.28
     salão
    0.28
     tensão
    0.27
    Act Density 0.001%

    No Known Activations