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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Overall
    -0.07
     transitioning
    -0.06
     Sitting
    -0.06
    _PB
    -0.06
     환산
    -0.06
    _MPI
    -0.06
    .Y
    -0.06
     test
    -0.06
     mediaPlayer
    -0.06
    	client
    -0.06
    POSITIVE LOGITS
     další
    0.07
    doch
    0.06
     Lucas
    0.06
     wonderful
    0.06
    eware
    0.06
     hashing
    0.06
    onne
    0.06
     přím
    0.05
     літ
    0.05
     periodically
    0.05
    Act Density 0.006%

    No Known Activations