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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash

    phrases that outline mathematical functions and their properties, particularly in the context of solutions to polynomial equations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects numeric tokens representing decimal (floating‐point) coefficients.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Nobody
    -0.08
    각
    -0.07
     Nobody
    -0.06
    Validate
    -0.06
    Along
    -0.06
     cm
    -0.06
    ене
    -0.06
    urd
    -0.06
    aud
    -0.06
    発表
    -0.06
    POSITIVE LOGITS
     chromium
    0.09
     �
    0.07
    .classes
    0.07
     csvfile
    0.07
    <|python_tag|>
    0.06
     mają
    0.06
    gzip
    0.06
     oldukça
    0.06
    CHEMY
    0.06
    ...");
↵
    0.06
    Act Density 0.021%

    No Known Activations