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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     durch
    -0.07
     David
    -0.07
    OMP
    -0.07
     rượu
    -0.06
    τό
    -0.06
     tst
    -0.06
     Hicks
    -0.06
    _tuple
    -0.06
    luet
    -0.06
    Group
    -0.06
    POSITIVE LOGITS
     Hannity
    0.07
    と思
    0.06
    inand
    0.06
     Dipl
    0.06
     Dodd
    0.06
     بشكل
    0.06
     shuttle
    0.06
     PAC
    0.06
    ozem
    0.06
    :bg
    0.06
    Act Density 0.132%

    No Known Activations