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

    Neuronpedia

    INDEX
    Explanations

    $_

    np_max-act · gemini-2.0-flash

    This neuron activates on PHP “$_” variable tokens (temporary variables prefixed with “$_”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    plot
    -0.08
     plot
    -0.08
    ak
    -0.07
     IC
    -0.07
    ák
    -0.07
     hitter
    -0.07
    /k
    -0.07
     cmap
    -0.07
     points
    -0.07
    Performance
    -0.07
    POSITIVE LOGITS
     $_
    0.08
    $_
    0.08
     Gren
    0.08
    Inspector
    0.07
     Zhao
    0.07
     giờ
    0.07
    %%%%%%%%%%%%%%%%
    0.07
    Our
    0.07
     gren
    0.07
     области
    0.07
    Act Density 0.004%

    No Known Activations