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

    Neuronpedia

    INDEX
    Explanations

    learning from experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fête
    -0.08
     oferecendo
    -0.08
    _layer
    -0.07
     menawarkan
    -0.07
     delicios
    -0.07
     lingu
    -0.07
     thriving
    -0.07
    ubl
    -0.07
     motor
    -0.07
     fiesta
    -0.07
    POSITIVE LOGITS
    惨
    0.11
     Lessons
    0.10
     हाद
    0.10
     lessons
    0.10
    elajaran
    0.10
     aches
    0.10
     painful
    0.10
    Lessons
    0.09
     Erfahrungen
    0.09
     erfaring
    0.09
    Act Density 0.103%

    No Known Activations