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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and technical parameters

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    align

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AspNetCore
    -0.50
    archiviato
    -0.49
     tartalomajánló
    -0.47
     getItemId
    -0.45
     tolua
    -0.42
    INCREF
    -0.42
     مواليد
    -0.40
    はじめに
    -0.40
    runApp
    -0.40
    UrlResolution
    -0.40
    POSITIVE LOGITS
    [toxicity=0]
    0.71
    GEBURTSDATUM
    0.69
    Diweddarwch
    0.59
    
    0.57
     leſs
    0.57
    0.57
    ſelves
    0.55
    Tikang
    0.55
     itſelf
    0.54
     faſt
    0.53
    Act Density 1.545%

    No Known Activations