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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IM
    -0.07
    ้จ
    -0.06
    -det
    -0.06
    об
    -0.06
     Become
    -0.06
    Write
    -0.06
     Failure
    -0.06
     सम
    -0.06
     opened
    -0.06
     Credits
    -0.06
    POSITIVE LOGITS
    .ServletException
    0.07
    (album
    0.07
    hone
    0.06
     ورد
    0.06
    _reaction
    0.06
    hall
    0.06
    xico
    0.06
    .util
    0.06
     Bitcoins
    0.06
    woord
    0.06
    Act Density 0.009%

    No Known Activations