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

    Neuronpedia

    INDEX
    Explanations

    Code/data entries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .putString
    -0.08
    anded
    -0.07
     دکتر
    -0.07
    any
    -0.06
    ispers
    -0.06
    чного
    -0.06
    -ish
    -0.06
    碎
    -0.06
    ่วย
    -0.06
    re
    -0.06
    POSITIVE LOGITS
    (rt
    0.06
    [strlen
    0.06
     massa
    0.06
     açısından
    0.06
     DIR
    0.06
     зміни
    0.06
    .MenuStrip
    0.06
     kab
    0.06
     trespass
    0.06
     imu
    0.06
    Act Density 0.026%

    No Known Activations