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

    Neuronpedia

    INDEX
    Explanations

    control group

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric measurement values (especially decimal or floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    $date
    -0.06
    	internal
    -0.06
     occurrence
    -0.06
     colours
    -0.06
    Checkbox
    -0.06
    (Path
    -0.06
     Conway
    -0.06
    _exec
    -0.06
     Mundo
    -0.06
    Smart
    -0.06
    POSITIVE LOGITS
     Rab
    0.07
     AN
    0.07
    ync
    0.07
    ???↵↵
    0.07
     flee
    0.07
    (C
    0.06
     ****
    0.06
     ödem
    0.06
     Did
    0.06
    ाई
    0.06
    Act Density 0.021%

    No Known Activations