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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that seem scientific or technical.

    oai_token-act-pair · gemini-2.0-flash

    and or other conjunctions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.79
    oneofs
    -0.77
     ostavi
    -0.71
     demografica
    -0.68
     мәкал
    -0.68
     Baillargeon
    -0.68
    ografija
    -0.67
     ✭✭
    -0.66
     Wicidata
    -0.65
    ibos
    -0.65
    POSITIVE LOGITS
     and
    0.90
    ,
    0.71
     и
    0.44
     &
    0.44
     (
    0.43
     AND
    0.42
    并且
    0.42
     or
    0.41
     nonché
    0.40
     그리고
    0.40
    Act Density 6.624%

    No Known Activations