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

    Neuronpedia

    INDEX
    Explanations

    variations and mentions of numerical values and their relationships

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

    number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.49
     reír
    -0.47
     asistir
    -0.45
     atraer
    -0.44
     optar
    -0.44
     soñar
    -0.42
     néglig
    -0.41
     acudir
    -0.40
     briefly
    -0.40
     durumda
    -0.40
    POSITIVE LOGITS
     getNumber
    0.77
     numbers
    0.74
    getNumber
    0.72
     BigNumber
    0.70
     Numbers
    0.69
     number
    0.69
     Number
    0.68
     randomNumber
    0.68
     numberWith
    0.68
    Numbers
    0.66
    Act Density 0.053%

    No Known Activations