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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bugs
    -0.06
    corn
    -0.06
    yun
    -0.06
    $__
    -0.06
    	load
    -0.06
     ersten
    -0.06
     excursion
    -0.06
    extern
    -0.06
    frames
    -0.06
    からの
    -0.06
    POSITIVE LOGITS
     freeze
    0.06
     rooft
    0.06
    offee
    0.06
    xBB
    0.06
    े�
    0.06
    .RES
    0.06
     lays
    0.06
    (pop
    0.06
     haut
    0.06
     enraged
    0.06
    Act Density 0.016%

    No Known Activations