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

    Neuronpedia

    INDEX
    Explanations

    examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    들이
    -0.06
     срав
    -0.06
     Beats
    -0.06
    .event
    -0.06
     unimagin
    -0.06
    Case
    -0.06
    	long
    -0.06
     şart
    -0.06
     finally
    -0.06
     cri
    -0.06
    POSITIVE LOGITS
    _memcpy
    0.07
    rchive
    0.06
    然后
    0.06
     librarian
    0.06
    <y
    0.06
     newsletter
    0.06
    _movies
    0.06
    .zip
    0.06
     NS
    0.06
     azt
    0.06
    Act Density 0.034%

    No Known Activations