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

    Neuronpedia

    INDEX
    Explanations

    column

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伯
    -0.07
    UserData
    -0.07
    fung
    -0.07
     dramas
    -0.06
     kar
    -0.06
    graphics
    -0.06
    haf
    -0.06
     jan
    -0.06
     JA
    -0.06
    .file
    -0.06
    POSITIVE LOGITS
    _REQ
    0.07
    (&$
    0.07
     waive
    0.07
     loa
    0.07
     đất
    0.06
    GHz
    0.06
    Doctors
    0.06
     Batı
    0.06
     Diy
    0.06
    \Console
    0.06
    Act Density 0.006%

    No Known Activations