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

    Neuronpedia

    INDEX
    Explanations

    formula boolean logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Screen
    -0.08
     manejo
    -0.08
     кирәк
    -0.08
     программы
    -0.07
     Screening
    -0.07
     solos
    -0.07
    vern
    -0.07
     мероприятия
    -0.07
    üste
    -0.07
     неабход
    -0.07
    POSITIVE LOGITS
    Cmp
    0.08
     zahval
    0.08
     결과
    0.08
     bogus
    0.08
     outcome
    0.08
     amistad
    0.08
     outrageous
    0.07
     hack
    0.07
     trick
    0.07
     Floyd
    0.07
    Act Density 0.008%

    No Known Activations