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

    Neuronpedia

    INDEX
    Explanations

    numerical data or mathematical symbols related to statistical analysis

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

    Numbers or single-digit numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers five through nine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.62
    parsedMessage
    -0.61
    extAlignment
    -0.58
     contextLoads
    -0.57
    BufferException
    -0.55
    三百
    -0.54
     للاسماء
    -0.53
    contentLoaded
    -0.52
     gynhyrchwyd
    -0.49
    elemField
    -0.48
    POSITIVE LOGITS
     seven
    1.09
     eight
    1.05
     six
    1.00
     nine
    0.96
     five
    0.90
     Eight
    0.89
     Seven
    0.85
    seven
    0.85
     SEVEN
    0.85
    eight
    0.82
    Act Density 0.946%

    No Known Activations