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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    23
    -0.08
    13
    -0.07
     Siz
    -0.07
     Jag
    -0.07
    173
    -0.06
     AlertDialog
    -0.06
         
    -0.06
     víc
    -0.06
     Panc
    -0.06
    	test
    -0.06
    POSITIVE LOGITS
     who
    0.16
    who
    0.14
     Who
    0.14
    Who
    0.12
     WHO
    0.10
    WHO
    0.08
    _under
    0.08
    opor
    0.08
    —who
    0.08
     Women
    0.07
    Act Density 0.097%

    No Known Activations