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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash

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

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     comforting
    -0.07
    (Api
    -0.06
    -messages
    -0.06
    151
    -0.06
    .Getenv
    -0.06
    16
    -0.06
    Msg
    -0.06
    Fair
    -0.06
    (alert
    -0.06
    uhe
    -0.06
    POSITIVE LOGITS
    ocumented
    0.07
    대학
    0.07
    ABOUT
    0.07
     Repos
    0.06
    新增
    0.06
     violence
    0.06
    θμ
    0.06
    gradation
    0.06
     agricult
    0.06
    .");↵
    0.06
    Act Density 0.051%

    No Known Activations