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

    Neuronpedia

    INDEX
    Explanations

    code related text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hawks
    -0.06
     Bundle
    -0.06
     BALL
    -0.06
     bas
    -0.06
    _BT
    -0.06
     anonym
    -0.06
     bomb
    -0.06
    _ORIENTATION
    -0.06
    955
    -0.06
    	ds
    -0.06
    POSITIVE LOGITS
    ATCH
    0.07
    >((
    0.06
    using
    0.06
    ини
    0.06
    atch
    0.06
     Courtesy
    0.06
    ateful
    0.06
    tickets
    0.06
    โป
    0.06
     Naked
    0.06
    Act Density 0.066%

    No Known Activations