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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usuario
    -0.08
     пан
    -0.07
     него
    -0.06
     leans
    -0.06
     vuông
    -0.06
     Rory
    -0.06
    věř
    -0.06
     soy
    -0.06
     FIFO
    -0.06
     gib
    -0.06
    POSITIVE LOGITS
    .stderr
    0.07
    .Inter
    0.06
     ".$_
    0.06
    -disable
    0.06
    (age
    0.06
    であった
    0.06
    ("{
    0.06
    .setProgress
    0.06
    μά
    0.06
    реть
    0.06
    Act Density 0.101%

    No Known Activations