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

    Neuronpedia

    INDEX
    Explanations

    terms and symbols related to mathematical concepts or variables

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

    macros defining constants and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.46
    BeginContext
    -0.44
    DeleteBehavior
    -0.43
    principalColumn
    -0.42
    ochet
    -0.41
     onAnimation
    -0.41
    ArrowToggle
    -0.40
    EndInit
    -0.40
    ReusableCell
    -0.40
    astéroïdes
    -0.40
    POSITIVE LOGITS
     فريبيس
    0.58
     propOrder
    0.54
    الدراسه
    0.48
    .*")]
    0.48
     nonUne
    0.47
    URLEncoder
    0.45
     صوتيه
    0.44
    مصادر
    0.44
     bParam
    0.42
     mug
    0.42
    Act Density 0.022%

    No Known Activations