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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Benef
    -0.07
     Chop
    -0.06
     authenticated
    -0.06
     разі
    -0.06
     Robertson
    -0.06
    put
    -0.06
     parenthesis
    -0.06
     Romney
    -0.06
     alternating
    -0.06
    _mark
    -0.06
    POSITIVE LOGITS
    enderror
    0.07
    شه
    0.07
    [char
    0.06
     hors
    0.06
     Jet
    0.06
     Hitler
    0.06
    753
    0.06
    kemiz
    0.06
     ihn
    0.06
    cwd
    0.06
    Act Density 0.001%

    No Known Activations