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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Porto
    -0.07
     eagerly
    -0.07
     transm
    -0.07
     rekomm
    -0.07
     slut
    -0.07
     وتن
    -0.07
     potr
    -0.07
     prestig
    -0.07
    кав
    -0.07
     Jones
    -0.07
    POSITIVE LOGITS
     dédi
    0.08
     dédié
    0.08
    даться
    0.08
    .component
    0.07
     Osh
    0.07
    @Component
    0.07
     મે
    0.07
    다가
    0.07
     посв
    0.07
    _unused
    0.07
    Act Density 1.297%

    No Known Activations