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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yaptı
    -0.08
     jednocze
    -0.08
     Make
    -0.07
     До
    -0.07
    怛
    -0.07
     المل
    -0.07
    ummer
    -0.07
     Bas
    -0.07
     contemplate
    -0.07
     GAM
    -0.07
    POSITIVE LOGITS
    מקומות
    0.07
    <Order
    0.07
    szą
    0.06
     rw
    0.06
     activist
    0.06
     rit
    0.06
    ei
    0.06
    خيارات
    0.06
     Structural
    0.06
    AI
    0.06
    Act Density 0.002%

    No Known Activations