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

    Neuronpedia

    INDEX
    Explanations

    Description/Setting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reference
    -0.07
    unately
    -0.06
    Flight
    -0.06
     respectively
    -0.06
     зако
    -0.06
     значит
    -0.06
    =username
    -0.06
    cznie
    -0.06
    تي
    -0.06
     Likely
    -0.06
    POSITIVE LOGITS
    adress
    0.06
    'int
    0.06
     čís
    0.06
    AAC
    0.06
     espect
    0.06
    .erb
    0.06
    mav
    0.06
     rotterdam
    0.06
    $arr
    0.06
    verage
    0.06
    Act Density 0.235%

    No Known Activations