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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    technical error messages related to Java applications.

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

    This neuron detects numeric tokens, especially floating‐point numbers (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     marty
    -0.07
     объ
    -0.07
    Tabla
    -0.06
    apping
    -0.06
     Korea
    -0.06
     перег
    -0.06
    ounder
    -0.06
    []=$
    -0.06
     putStrLn
    -0.06
    ylie
    -0.06
    POSITIVE LOGITS
     schedule
    0.06
    /includes
    0.06
    alian
    0.06
    +l
    0.06
     Hamm
    0.06
     слух
    0.06
    สถานท
    0.06
    shall
    0.06
    تون
    0.06
     ))
    0.06
    Act Density 0.002%

    No Known Activations