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

    Neuronpedia

    INDEX
    Explanations

    despite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     standalone
    -0.07
     elast
    -0.07
    面临
    -0.07
    .Control
    -0.07
    Jesteś
    -0.06
    +t
    -0.06
    abic
    -0.06
    /test
    -0.06
    Strong
    -0.06
     Bans
    -0.06
    POSITIVE LOGITS
    !--
    0.07
     resumes
    0.07
     must
    0.07
    invalidate
    0.07
    вест
    0.06
     quên
    0.06
    鹗
    0.06
    �
    0.06
    rysler
    0.06
     phú
    0.06
    Act Density 0.037%

    No Known Activations