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

    Neuronpedia

    INDEX
    Explanations

    yes or no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nova
    -0.07
    (!$
    -0.07
    .paginator
    -0.06
    학교
    -0.06
    chunk
    -0.06
     ngôn
    -0.06
     hemos
    -0.06
    mí
    -0.06
     Specialists
    -0.06
     порядок
    -0.06
    POSITIVE LOGITS
    .Ma
    0.06
    practice
    0.06
    utowired
    0.06
    -leaning
    0.06
    graduate
    0.06
    ubu
    0.06
    jspx
    0.06
    ftware
    0.06
    seen
    0.06
    ähl
    0.06
    Act Density 0.009%

    No Known Activations