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

    Neuronpedia

    INDEX
    Explanations

    Mathematical notation

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on numeric literals, especially floating‐point or decimal numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    COVERY
    -0.07
    uml
    -0.07
     "\<
    -0.07
    ⠀⠀
    -0.06
     �
    -0.06
    irebase
    -0.06
    /tcp
    -0.06
    rored
    -0.06
    ￣
    -0.06
     fragile
    -0.06
    POSITIVE LOGITS
     nhé
    0.07
     neoliberal
    0.06
    .standard
    0.06
     губер
    0.06
     nhập
    0.06
    .cornerRadius
    0.06
     ilç
    0.06
    BitConverter
    0.06
     unitOfWork
    0.06
     zá
    0.06
    Act Density 0.025%

    No Known Activations