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

    Neuronpedia

    INDEX
    Explanations

    references to technical specifications and performance metrics

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

    starting with "Sp" or containing "fract"

    np_acts-logits-general · gemini-2.0-flash

    Sp words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.81
    twimg
    -0.75
    Varint
    -0.74
     OMITBAD
    -0.74
    MLLoader
    -0.73
    NameInMap
    -0.72
    WindowConstants
    -0.69
     Dario
    -0.68
    GraphicsUnit
    -0.67
    SourceChecksum
    -0.67
    POSITIVE LOGITS
     Sp
    2.26
    Sp
    2.18
     SP
    2.11
     sp
    2.05
    SP
    2.02
    sp
    1.98
     Spencer
    1.88
    Spencer
    1.79
     Spa
    1.73
     Spe
    1.70
    Act Density 0.570%

    No Known Activations