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

    Neuronpedia

    INDEX
    Explanations

    backticks used in SQL code syntax

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

    database operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     définiti
    -0.47
     metálica
    -0.44
    willReturn
    -0.40
     africains
    -0.40
     coute
    -0.40
     deberes
    -0.39
     financiera
    -0.39
     prů
    -0.38
    Спољашње
    -0.38
     rápidos
    -0.38
    POSITIVE LOGITS
    `.`
    0.66
     [`
    0.60
     defaultstate
    0.59
     `
    0.59
    __(/*!
    0.57
     "`
    0.56
    SerializedName
    0.56
     CreateTagHelper
    0.54
    astify
    0.50
     iload
    0.48
    Act Density 0.016%

    No Known Activations