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

    Neuronpedia

    INDEX
    Explanations

    y-coordinates

    np_max-act · gemini-2.0-flash

    The neuron detects floating-point numerical literals (i.e. numbers containing a decimal point) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    usters
    -0.07
     Laboratories
    -0.07
     Babies
    -0.07
    wing
    -0.07
     Mile
    -0.06
    nego
    -0.06
     fra
    -0.06
     Significant
    -0.06
     stream
    -0.06
     eliminate
    -0.06
    POSITIVE LOGITS
     держави
    0.07
    	defer
    0.06
     площад
    0.06
    (`${
    0.06
     площ
    0.06
     муль
    0.06
    $path
    0.06
    аксим
    0.06
     Gaza
    0.06
     WAN
    0.06
    Act Density 0.177%

    No Known Activations