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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drž
    -0.07
    _<?
    -0.07
     зокрема
    -0.06
    تون
    -0.06
    дем
    -0.06
     sick
    -0.06
     Large
    -0.06
    ex
    -0.06
     دع
    -0.06
    ($"{
    -0.06
    POSITIVE LOGITS
     Vitamin
    0.07
     assignable
    0.06
     portray
    0.06
    245
    0.06
     UPLOAD
    0.06
     různ
    0.06
     fit
    0.06
    ＼↵
    0.06
    (Display
    0.06
     pathway
    0.06
    Act Density 0.022%

    No Known Activations