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

    Neuronpedia

    INDEX
    Explanations

    common short words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Winners
    -0.07
    حي
    -0.06
     Julian
    -0.06
     panels
    -0.06
    407
    -0.06
    AW
    -0.06
    grow
    -0.06
     regulator
    -0.06
    ου
    -0.06
     drills
    -0.06
    POSITIVE LOGITS
     Integer
    0.07
    .getNum
    0.07
    RoutingModule
    0.07
     전용면적
    0.07
    .Inv
    0.06
     heir
    0.06
    .]↵↵
    0.06
    .notifyDataSetChanged
    0.06
     pprint
    0.06
    .timeScale
    0.06
    Act Density 0.000%

    No Known Activations