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
    وقيت
    -0.07
    基地
    -0.06
    consider
    -0.06
    gend
    -0.06
     Kanun
    -0.06
    음을
    -0.06
    WEBPACK
    -0.06
    Serialize
    -0.06
    LowerCase
    -0.06
     मई
    -0.06
    POSITIVE LOGITS
     prevents
    0.07
     autonomy
    0.06
     listing
    0.06
     (**
    0.06
     lieutenant
    0.06
    .Standard
    0.06
     Rosenberg
    0.06
    風
    0.06
     Borg
    0.06
    .Unity
    0.06
    Act Density 0.000%

    No Known Activations