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

    Neuronpedia

    INDEX
    Explanations

    People

    np_max-act · gemini-2.0-flash

    The neuron is keyed to spotting numeric tokens—especially decimal‐point numbers—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     te
    -0.07
     participates
    -0.07
     ESC
    -0.06
     occ
    -0.06
     critical
    -0.06
     novel
    -0.06
     Animal
    -0.06
    rpm
    -0.06
     Τε
    -0.06
     RCS
    -0.06
    POSITIVE LOGITS
    ivities
    0.06
    الأ
    0.06
    матрива
    0.06
    ู่
    0.06
    ?\
    0.06
     коштів
    0.06
    CanBeConverted
    0.06
     منها
    0.06
     #=>
    0.06
    (sql
    0.06
    Act Density 0.036%

    No Known Activations