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

    Neuronpedia

    INDEX
    Explanations

    -safe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    दम
    -0.07
     ل
    -0.07
     z
    -0.07
     railway
    -0.07
    fgang
    -0.07
     rainy
    -0.06
     atmos
    -0.06
     ::=
    -0.06
    ΙΚΟ
    -0.06
     "\(
    -0.06
    POSITIVE LOGITS
    _sample
    0.07
    	TRACE
    0.07
     investigate
    0.06
     XPAR
    0.06
    해
    0.06
     #
    0.06
     Rich
    0.06
     searchTerm
    0.06
    .setY
    0.06
     희
    0.06
    Act Density 0.001%

    No Known Activations