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

    Neuronpedia

    INDEX
    Explanations

    Recovering from mistakes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sn
    -0.07
     Watkins
    -0.07
    تراث
    -0.07
    딛
    -0.06
    _mult
    -0.06
    _pm
    -0.06
     Administrative
    -0.06
    起き
    -0.06
    馔
    -0.06
     Op
    -0.06
    POSITIVE LOGITS
     PIL
    0.07
    (argument
    0.07
    Setter
    0.07
     paginator
    0.07
    refer
    0.07
    Github
    0.07
    -input
    0.07
    	CG
    0.07
    phoon
    0.06
     теат
    0.06
    Act Density 0.024%

    No Known Activations