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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (loop
    -0.07
    ctr
    -0.06
    "Some
    -0.06
     signals
    -0.06
    	loop
    -0.06
    РН
    -0.06
     Rendering
    -0.06
     engagement
    -0.06
     property
    -0.06
    nten
    -0.06
    POSITIVE LOGITS
    @Before
    0.07
    ayın
    0.07
    _WE
    0.07
     Yu
    0.07
     đầu
    0.06
     Cush
    0.06
    .SH
    0.06
    ää
    0.06
     UNUSED
    0.06
     длин
    0.06
    Act Density 0.019%

    No Known Activations