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

    Neuronpedia

    INDEX
    Explanations

    bis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Almanya
    -0.06
    _ll
    -0.06
     arrogant
    -0.06
     Guill
    -0.06
     вул
    -0.06
     sollen
    -0.06
     수가
    -0.06
    осред
    -0.06
     px
    -0.06
    [MAX
    -0.06
    POSITIVE LOGITS
    IS
    0.09
    cis
    0.09
     cis
    0.08
    is
    0.07
    JOB
    0.07
    isle
    0.07
    ис
    0.07
     rigid
    0.06
    ysis
    0.06
    bis
    0.06
    Act Density 0.011%

    No Known Activations