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

    Neuronpedia

    INDEX
    Explanations

    How

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [m
    -0.07
    ,address
    -0.07
     Capture
    -0.07
    ی
    -0.07
     要
    -0.06
    >%
    -0.06
    득
    -0.06
    	u
    -0.06
    �
    -0.06
    antly
    -0.06
    POSITIVE LOGITS
    How
    0.07
     How
    0.07
     Cosby
    0.07
     Scr
    0.06
    <Func
    0.06
    What
    0.06
    lac
    0.06
    égor
    0.06
     Flint
    0.06
     béné
    0.06
    Act Density 0.028%

    No Known Activations