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

    Neuronpedia

    INDEX
    Explanations

    code indices

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Uint
    -0.08
     degli
    -0.06
     такие
    -0.06
     Fraser
    -0.06
     dosp
    -0.06
    IColor
    -0.06
    /*↵↵
    -0.06
    ué
    -0.06
     کارگرد
    -0.06
     alertDialog
    -0.06
    POSITIVE LOGITS
    (shader
    0.06
    "./
    0.06
    ICO
    0.06
     بدن
    0.06
     compartments
    0.06
     ilk
    0.06
    imiter
    0.06
    %'↵
    0.06
    hen
    0.06
     Trade
    0.06
    Act Density 0.005%

    No Known Activations