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

    Neuronpedia

    INDEX
    Explanations

    ups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    新区
    -0.08
    	lp
    -0.08
     zainteres
    -0.08
    Libre
    -0.07
    DSM
    -0.07
     limpia
    -0.07
     collide
    -0.07
    介
    -0.07
     pře
    -0.07
     specialize
    -0.07
    POSITIVE LOGITS
     ginn
    0.10
     iterations
    0.10
    _iterations
    0.09
    Iterations
    0.09
    次数
    0.08
     físico
    0.08
     количества
    0.08
     хлоп
    0.08
     tasks
    0.08
     Iter
    0.07
    Act Density 0.007%

    No Known Activations