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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Notification
    -0.07
     allege
    -0.06
    เตอร
    -0.06
     Seventh
    -0.06
    describe
    -0.06
    NaN
    -0.06
     COPYRIGHT
    -0.06
     Squadron
    -0.06
    зна
    -0.06
    secutive
    -0.06
    POSITIVE LOGITS
    394
    0.07
     соп
    0.07
     mot
    0.06
    	person
    0.06
     trest
    0.06
    prov
    0.06
     rencontrer
    0.06
     ap
    0.06
     li
    0.06
    بر
    0.06
    Act Density 0.128%

    No Known Activations