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

    Neuronpedia

    INDEX
    Explanations

    simplicity/ity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ǎ
    -0.07
     verse
    -0.06
    isAdmin
    -0.06
    startswith
    -0.06
    通过
    -0.06
     مغ
    -0.06
    ihn
    -0.06
     потім
    -0.06
     král
    -0.06
     stderr
    -0.06
    POSITIVE LOGITS
    stered
    0.07
     Topics
    0.07
    Getty
    0.07
    $result
    0.07
    enberg
    0.06
    yps
    0.06
    Illegal
    0.06
    (MPI
    0.06
    ibile
    0.06
     Hawth
    0.06
    Act Density 0.014%

    No Known Activations