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

    Neuronpedia

    INDEX
    Explanations

    code or documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     가지
    -0.07
     tuples
    -0.07
     επισ
    -0.07
    list
    -0.06
    MP
    -0.06
     дея
    -0.06
     feeder
    -0.06
     Questions
    -0.06
    ilmesi
    -0.06
    logger
    -0.06
    POSITIVE LOGITS
    ㅎ
    0.07
    "L
    0.06
     planes
    0.06
     
    0.06
    ’une
    0.06
    "D
    0.06
    roma
    0.06
     apost
    0.06
     Kota
    0.06
     něj
    0.06
    Act Density 0.090%

    No Known Activations