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

    Neuronpedia

    INDEX
    Explanations

    instances of the contraction "don't" and related negations

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

    patient disease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.66
     BoxDecoration
    -0.65
     ویکی‌پدیا
    -0.64
     Infórmanos
    -0.63
     createContext
    -0.63
    AnchorStyles
    -0.61
    RTLR
    -0.59
     BoxFit
    -0.59
    ruptedException
    -0.58
    OGND
    -0.58
    POSITIVE LOGITS
    ´
    1.45
     ´
    1.10
    ´)
    0.75
     `
    0.70
    (´
    0.68
     ¨
    0.65
    (`
    0.63
    ¨
    0.59
    `
    0.54
     (`
    0.52
    Act Density 0.006%

    No Known Activations