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

    Neuronpedia

    INDEX
    Explanations

    center

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TRACE
    -0.07
     deviations
    -0.07
    Angle
    -0.07
    	Address
    -0.07
    (object
    -0.06
    	e
    -0.06
     directions
    -0.06
    	B
    -0.06
     VOID
    -0.06
     loader
    -0.06
    POSITIVE LOGITS
    襲
    0.06
     jov
    0.06
    銷
    0.06
    庆
    0.06
    ấu
    0.06
    pcs
    0.06
     bí
    0.06
     hone
    0.06
    쇼
    0.06
    濟
    0.06
    Act Density 0.008%

    No Known Activations