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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numeric values (decimal measurements) in technical contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -Se
    -0.07
     Basil
    -0.07
     Francisco
    -0.07
     partnering
    -0.07
     titan
    -0.07
     Frances
    -0.07
     Sinai
    -0.06
     Trials
    -0.06
    	text
    -0.06
     puss
    -0.06
    POSITIVE LOGITS
     displaying
    0.06
     अव
    0.06
    تها
    0.06
     راه
    0.06
    ذا
    0.06
     pipes
    0.06
    		↵↵
    0.06
    delimiter
    0.06
     προϊ
    0.06
     //!↵
    0.06
    Act Density 0.003%

    No Known Activations