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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and variables related to physical models and calculations

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

    Mathematical or physical equations

    np_acts-logits-general · gemini-2.0-flash

    scaling parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    väg
    -0.55
     humaines
    -0.44
     berusia
    -0.43
     verksamhet
    -0.43
     maisha
    -0.41
     vertes
    -0.41
     celebrado
    -0.40
     männis
    -0.40
     beina
    -0.40
    ukasz
    -0.40
    POSITIVE LOGITS
     متعلقه
    0.97
    脚注の使い方
    0.95
    contentLoaded
    0.89
    WebElementEntity
    0.88
    ///</
    0.87
    expandindo
    0.84
    enderror
    0.83
    sizeCache
    0.80
    ">—
    0.79
    TagMode
    0.78
    Act Density 1.031%

    No Known Activations