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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     THEN
    -0.07
     보면
    -0.07
     then
    -0.07
    Await
    -0.07
    ("{
    -0.07
    (pr
    -0.06
    -r
    -0.06
    -order
    -0.06
    ;i
    -0.06
     hotel
    -0.06
    POSITIVE LOGITS
     μπ
    0.07
     �
    0.07
     grp
    0.07
     mong
    0.07
     pleasantly
    0.06
     nginx
    0.06
    および
    0.06
    带
    0.06
    _browser
    0.06
    uiltin
    0.06
    Act Density 0.024%

    No Known Activations