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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron fires on the little decimal‐point numbers that appear in legal citations (i.e. page or reporter references expressed as floats).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Control
    -0.06
     Puzzle
    -0.06
    озв
    -0.06
     lọc
    -0.06
    ิค
    -0.06
     lean
    -0.06
     drunk
    -0.06
     survival
    -0.06
     thirst
    -0.06
    ekler
    -0.06
    POSITIVE LOGITS
     birden
    0.07
     Chemistry
    0.06
     ENGINE
    0.06
    bove
    0.06
    午
    0.06
     Def
    0.06
    (always
    0.06
    세요
    0.06
     Claim
    0.06
    -describedby
    0.06
    Act Density 0.000%

    No Known Activations