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

    Neuronpedia

    INDEX
    Explanations

    Rotary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thesize
    -0.07
    udiante
    -0.06
     Palo
    -0.06
    .si
    -0.06
    Back
    -0.06
     Brushes
    -0.06
    舌
    -0.06
     прор
    -0.06
    ameleon
    -0.06
    Wall
    -0.06
    POSITIVE LOGITS
     стор
    0.08
     noqa
    0.08
     یه
    0.07
     Reserve
    0.07
     tough
    0.07
     реги
    0.06
     bli
    0.06
     tightening
    0.06
     DialogInterface
    0.06
     Rotary
    0.06
    Act Density 0.002%

    No Known Activations