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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and calculations

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

    Variables, often single letters, within mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.62
    ThemeOverlay
    -0.59
    WriteBarrier
    -0.59
     Himo
    -0.59
    OGND
    -0.57
    انيف
    -0.56
    Strap
    -0.55
    )$_
    -0.55
    ]**
    -0.55
    richTextPanel
    -0.55
    POSITIVE LOGITS
     rowspan
    0.58
    prepareStatement
    0.56
    :+:
    0.53
     démocr
    0.51
    eadilan
    0.47
    UIControlState
    0.47
     appartenant
    0.47
    gnąć
    0.46
    шайте
    0.46
    󠁢
    0.45
    Act Density 1.362%

    No Known Activations