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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     社
    -0.06
    alim
    -0.06
    کر
    -0.06
    เกาะ
    -0.06
    anca
    -0.06
     arada
    -0.06
     multin
    -0.06
     spectacle
    -0.06
    那里
    -0.06
    etric
    -0.06
    POSITIVE LOGITS
    _Top
    0.07
     взрос
    0.07
     змін
    0.07
     RSVP
    0.06
    _pcm
    0.06
     Genç
    0.06
     كنت
    0.06
     Ant
    0.06
     slož
    0.06
     Uran
    0.06
    Act Density 0.006%

    No Known Activations