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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    the presence of floating-point numbers (decimal tokens, e.g. “0.66”, “1.20”, etc.)

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    numbers related to lottery games.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    evaluate
    -0.07
    \Traits
    -0.07
     kt
    -0.06
    OLD
    -0.06
     obe
    -0.06
    git
    -0.06
    ाकर
    -0.06
     IICIII
    -0.06
     γρα
    -0.06
    POSITIVE LOGITS
     Discounts
    0.07
     εισ
    0.07
    (message
    0.07
    //#
    0.06
     μην
    0.06
     opportunities
    0.06
    564
    0.06
     nep
    0.06
    Cliente
    0.06
    <Button
    0.06
    Act Density 0.006%

    No Known Activations