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
    edge
    -0.07
     coined
    -0.06
     robots
    -0.06
    ук
    -0.06
     bunk
    -0.06
     オ
    -0.06
    	cache
    -0.06
     principals
    -0.06
     patient
    -0.06
     Parameter
    -0.06
    POSITIVE LOGITS
    γεν
    0.07
     Beau
    0.07
     krás
    0.07
     Lv
    0.06
    /fontawesome
    0.06
     مناطق
    0.06
     μία
    0.06
    χει
    0.06
    iver
    0.06
    _Tis
    0.06
    Act Density 0.005%

    No Known Activations