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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

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

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Users
    -0.07
    aincontri
    -0.07
    eron
    -0.07
    环
    -0.07
     kteří
    -0.06
     MIN
    -0.06
    deriv
    -0.06
    acre
    -0.06
     заболеваний
    -0.06
    ottesville
    -0.06
    POSITIVE LOGITS
     확
    0.06
    	element
    0.06
     @[
    0.06
    -ng
    0.06
     năng
    0.06
    /Instruction
    0.06
     Hugh
    0.06
     Cortex
    0.06
                     
    0.06
     Sew
    0.06
    Act Density 0.002%

    No Known Activations