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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to the importance, assumptions, and characteristics of scientific or legal research.

    oai_token-act-pair · gemini-2.0-flash

    importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     importance
    -1.66
    importance
    -1.45
     Importance
    -1.35
     priority
    -1.27
    Importance
    -1.25
     significance
    -1.20
     importancia
    -1.17
     importância
    -1.13
     Priority
    -1.13
    priority
    -1.13
    POSITIVE LOGITS
     []:
    0.75
     autorytatywna
    0.58
    CrossRef
    0.56
    󠁮
    0.54
    gesamt
    0.54
     وتسجيلات
    0.53
     coû
    0.52
    MemoryWarning
    0.50
     ErrIntOverflow
    0.48
    drawSprites
    0.48
    Act Density 15.221%

    No Known Activations