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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    เช
    -0.06
     landscape
    -0.06
    -0.06
    #
    -0.06
    Steam
    -0.06
    Ip
    -0.06
    ands
    -0.05
    reflection
    -0.05
     southern
    -0.05
    _Up
    -0.05
    POSITIVE LOGITS
    (TABLE
    0.07
    (outputs
    0.06
    isbn
    0.06
     ارسال
    0.06
    -fin
    0.06
     Phó
    0.06
    leDb
    0.06
    .modelo
    0.06
     учнів
    0.06
    lexical
    0.06
    Act Density 0.190%

    No Known Activations