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

    Neuronpedia

    INDEX
    Explanations

    specific food-related items and cooking techniques

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

    objects, materials, and parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.52
     Municipalidad
    -0.51
    UrlResolution
    -0.51
     المعيارى
    -0.49
     HasFactory
    -0.47
     diputado
    -0.47
     direta
    -0.46
     progrès
    -0.46
    ándome
    -0.46
     enfans
    -0.46
    POSITIVE LOGITS
    ModelAttribute
    0.51
     مشين
    0.49
     scratch
    0.42
     Manip
    0.41
     fen
    0.39
     plugs
    0.38
     фе
    0.38
     Scratch
    0.38
     noodles
    0.37
     LEGO
    0.37
    Act Density 0.020%

    No Known Activations