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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flights
    -0.08
    Completed
    -0.08
     행
    -0.07
     fantasy
    -0.07
     fascia
    -0.07
     completed
    -0.07
     basic
    -0.07
     seat
    -0.07
     correct
    -0.07
     fab
    -0.07
    POSITIVE LOGITS
     evolve
    0.10
    initial
    0.10
    	initial
    0.10
     recursively
    0.09
    _initial
    0.09
     evolves
    0.09
    (initial
    0.09
    Initially
    0.09
     Initially
    0.09
     Ecos
    0.09
    Act Density 0.042%

    No Known Activations