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

    Neuronpedia

    INDEX
    Explanations

    Software descriptions/documentation

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens containing a decimal point (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ver
    -0.07
    .de
    -0.07
    蕉
    -0.07
     ware
    -0.07
     hled
    -0.07
    ,e
    -0.07
     rostlin
    -0.06
     ver
    -0.06
    959
    -0.06
     gown
    -0.06
    POSITIVE LOGITS
    搭
    0.08
    -back
    0.07
     tackle
    0.06
    -fi
    0.06
     recession
    0.06
     Pell
    0.06
    -port
    0.06
    	className
    0.06
     Premium
    0.06
     PIL
    0.06
    Act Density 0.000%

    No Known Activations