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

    Neuronpedia

    INDEX
    Explanations

    win

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cljs
    -0.07
     菲律宾申博
    -0.07
    ็น
    -0.07
    _WORK
    -0.07
    íg
    -0.07
    (List
    -0.06
    	fire
    -0.06
    �
    -0.06
    _k
    -0.06
     δη
    -0.06
    POSITIVE LOGITS
     complement
    0.06
    Prem
    0.06
     divider
    0.06
     Excellence
    0.06
    Extract
    0.06
     implanted
    0.06
     chac
    0.06
     Sales
    0.06
     swallowing
    0.06
    CONFIG
    0.06
    Act Density 0.020%

    No Known Activations