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

    Neuronpedia

    INDEX
    Explanations

    Scientific abstracts

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric measurement tokens—especially floating‐point values or decimals denoting experimental data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -definition
    -0.07
    rights
    -0.07
    (fname
    -0.07
     medicine
    -0.07
     spherical
    -0.06
    cot
    -0.06
    Many
    -0.06
     downturn
    -0.06
    タル
    -0.06
    -course
    -0.06
    POSITIVE LOGITS
    <tag
    0.07
    olucion
    0.06
     �
    0.06
    isSelected
    0.06
     удив
    0.06
     JSX
    0.06
    ongoose
    0.06
     새글
    0.06
    сит
    0.06
    ilit
    0.06
    Act Density 0.088%

    No Known Activations