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

    Neuronpedia

    INDEX
    Explanations

    </

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kp
    -0.08
     yapmak
    -0.08
    바이
    -0.07
    	ev
    -0.07
     laat
    -0.07
    Beat
    -0.07
     pall
    -0.07
    Lot
    -0.07
    rets
    -0.07
     прев
    -0.07
    POSITIVE LOGITS
    Into
    0.08
     in
    0.08
     โ
    0.08
     Johnson
    0.07
     住
    0.07
    _under
    0.07
    _tokens
    0.07
     Isn
    0.07
     don
    0.07
     MessageBoxButtons
    0.06
    Act Density 0.016%

    No Known Activations