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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     नजर
    -0.07
     Planned
    -0.07
    ’
    -0.07
    -ahead
    -0.07
    -than
    -0.06
     бо
    -0.06
     Tyson
    -0.06
    ど
    -0.06
    ัปดาห
    -0.06
    า
    -0.06
    POSITIVE LOGITS
    ربی
    0.07
     Совет
    0.06
     совершенно
    0.06
    ويت
    0.06
     quota
    0.06
     perv
    0.06
    属于
    0.06
    .squeeze
    0.06
    leftJoin
    0.06
     vtk
    0.06
    Act Density 0.009%

    No Known Activations