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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace in code or script-like text

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

    mathematical and programming notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.74
     otomatig
    -0.62
     للاسماء
    -0.58
    DispatchToProps
    -0.56
    fromnode
    -0.55
    RenderAtEndOf
    -0.53
     Италијани
    -0.53
    ParallelGroup
    -0.52
     ſtate
    -0.48
    verifyException
    -0.47
    POSITIVE LOGITS
    duled
    0.46
     despe
    0.45
     disfr
    0.43
    exitRule
    0.41
     appelez
    0.40
    taining
    0.40
    ographia
    0.40
    achios
    0.39
     ждать
    0.39
     hưởng
    0.39
    Act Density 0.027%

    No Known Activations