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

    Neuronpedia

    INDEX
    Explanations

    specific instances of the word "sobre" and other terms related to measurement or characteristics

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

    sobre suas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     démocr
    -0.54
    Fernseh
    -0.51
    éroport
    -0.50
    categoryName
    -0.49
     Espíritu
    -0.49
     ainfi
    -0.49
     fédé
    -0.48
    Nucl
    -0.48
    Artwork
    -0.48
     kasarigan
    -0.48
    POSITIVE LOGITS
     sobre
    1.69
     Sobre
    1.44
     SOBRE
    1.42
    sobre
    1.41
    Sobre
    1.37
    SOBRE
    0.92
     about
    0.87
    about
    0.86
     über
    0.85
     tentang
    0.80
    Act Density 0.002%

    No Known Activations