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

    Neuronpedia

    INDEX
    Explanations

    references to numeric values and their relationships in a mathematical context

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

    Mathematical or physics context

    np_acts-logits-general · gemini-2.0-flash

    two-dimensional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DataAnnotations
    -0.64
    ंदीखरीदारी
    -0.61
     htons
    -0.54
    География
    -0.54
     InputDecoration
    -0.50
    beten
    -0.50
    LError
    -0.50
    ândia
    -0.50
    Afrique
    -0.49
     geb
    -0.48
    POSITIVE LOGITS
     dimensional
    0.72
    component
    0.63
    dimensional
    0.59
    way
    0.59
    ary
    0.58
    ufig
    0.56
    Dimensional
    0.56
     Dimensional
    0.56
     component
    0.56
    stage
    0.55
    Act Density 0.633%

    No Known Activations