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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

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

    Fractions with negative signs

    np_acts-logits-general · gemini-2.0-flash

    division and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stra
    -0.56
    gle
    -0.49
    estr
    -0.46
    梨
    -0.45
    Vidite
    -0.44
    :[]
    -0.44
    lema
    -0.43
    Telegram
    -0.43
     المعيارى
    -0.43
    yy
    -0.43
    POSITIVE LOGITS
    AddTagHelper
    0.78
    Tikang
    0.72
    NameInMap
    0.70
    Half
    0.65
    SizeF
    0.64
    half
    0.64
    AndEndTag
    0.64
    DebuggerNonUser
    0.64
    HomeAsUpEnabled
    0.64
    UnusedPrivate
    0.63
    Act Density 1.165%

    No Known Activations