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

    Neuronpedia

    INDEX
    Explanations

    DS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cz
    -0.06
    ">

↵
    -0.06
    DrawerToggle
    -0.06
     skepticism
    -0.06
     vystav
    -0.06
     inşa
    -0.06
    sWith
    -0.06
     sewer
    -0.06
     zdrav
    -0.06
    авлива
    -0.06
    POSITIVE LOGITS
    402
    0.07
    mot
    0.07
     "{{
    0.06
     abdom
    0.06
    (comp
    0.06
     mot
    0.06
     coi
    0.06
     sexes
    0.06
     검
    0.06
    storm
    0.06
    Act Density 0.000%

    No Known Activations