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

    Neuronpedia

    INDEX
    Explanations

    Dialogue and strong opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     숙
    -0.07
    SMART
    -0.07
    .Rest
    -0.07
    291
    -0.06
     Apart
    -0.06
    스테
    -0.06
    (guild
    -0.06
    .Bottom
    -0.06
     tast
    -0.06
     forecast
    -0.06
    POSITIVE LOGITS
    ewitness
    0.07
     closeButton
    0.07
    odie
    0.07
    �
    0.07
    .pushButton
    0.07
     wb
    0.06
     mog
    0.06
    وار
    0.06
     kat
    0.06
    Ik
    0.06
    Act Density 0.031%

    No Known Activations