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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and variables related to function definitions and operations

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

    LaTeX math symbols

    np_acts-logits-general · gemini-2.0-flash

    followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noires
    -0.59
    }}+
    -0.57
     nuages
    -0.57
    })+
    -0.57
     }}-
    -0.55
     contemporain
    -0.54
     célèbres
    -0.53
     tetto
    -0.53
     enfans
    -0.52
    Filmografie
    -0.52
    POSITIVE LOGITS
    +
    0.97
    -
    0.75
     +
    0.73
    ArgumentParser
    0.66
    bootstrapcdn
    0.65
    -£
    0.64
    −
    0.63
     -
    0.63
     unknownFields
    0.58
     незавершена
    0.57
    Act Density 1.307%

    No Known Activations