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

    Neuronpedia

    INDEX
    Explanations

    set theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kul
    -0.08
    Kul
    -0.07
    .live
    -0.07
     estimated
    -0.07
     Rund
    -0.07
     pensioen
    -0.07
    續
    -0.07
    _buffers
    -0.07
    estimated
    -0.07
     ഉണ്ടായ
    -0.07
    POSITIVE LOGITS
    озя
    0.08
     Basically
    0.08
     เอ
    0.08
    ่อน
    0.08
     jól
    0.08
    lady
    0.08
     intéressant
    0.08
     asker
    0.07
     bester
    0.07
     Essentially
    0.07
    Act Density 0.009%

    No Known Activations