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

    Neuronpedia

    INDEX
    Explanations

    suggestions

    np_max-act · gemini-2.0-flash

    This neuron activates on decimal numeric literals (floating-point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     plu
    -0.07
    gp
    -0.07
     insecure
    -0.07
    ，默认
    -0.07
     policemen
    -0.06
     dospěl
    -0.06
     DB
    -0.06
     catches
    -0.06
     WEIGHT
    -0.06
    형
    -0.06
    POSITIVE LOGITS
    street
    0.06
     poverty
    0.06
     κατα
    0.06
     Cornwall
    0.06
    {o
    0.06
     Lenovo
    0.06
    웅
    0.06
     Carolyn
    0.06
    <F
    0.06
     RaisePropertyChanged
    0.06
    Act Density 0.169%

    No Known Activations