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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hal
    -0.07
    цу
    -0.07
    suit
    -0.07
    (ls
    -0.06
    .DataBindings
    -0.06
    bou
    -0.06
    erture
    -0.06
    ocomplete
    -0.06
    iteli
    -0.06
     Next
    -0.06
    POSITIVE LOGITS
    .xtext
    0.07
    BW
    0.07
    stants
    0.06
    拉
    0.06
     ----------↵
    0.06
     přesně
    0.06
    	page
    0.06
    毛
    0.06
     mềm
    0.06
    cheng
    0.06
    Act Density 0.002%

    No Known Activations