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

    Neuronpedia

    INDEX
    Explanations

    encoding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    3
    -0.08
    wear
    -0.07
    sz
    -0.07
    /software
    -0.07
     し
    -0.06
    .day
    -0.06
     membres
    -0.06
    BMI
    -0.06
    763
    -0.06
    (sz
    -0.06
    POSITIVE LOGITS
    uling
    0.06
     ayant
    0.06
    меч
    0.06
     tras
    0.06
     Plug
    0.06
    tık
    0.06
     بج
    0.06
     دف
    0.06
     anlamda
    0.06
    .par
    0.06
    Act Density 0.001%

    No Known Activations