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

    Neuronpedia

    INDEX
    Explanations

    elements related to structured data and calculations

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

    Mathematical or arithmetic expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     standard
    -0.54
    ",{
    -0.53
    vie
    -0.52
     cop
    -0.52
     Cop
    -0.52
     nar
    -0.51
    pik
    -0.51
    inete
    -0.51
     Co
    -0.50
    fra
    -0.50
    POSITIVE LOGITS
     myſelf
    0.85
     poffible
    0.85
    RectangleBorder
    0.83
     متعلقه
    0.82
     pleaſure
    0.78
    WebControls
    0.74
     aDecoder
    0.74
     houſe
    0.74
     purpoſe
    0.73
     beſt
    0.73
    Act Density 0.376%

    No Known Activations