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

    Neuronpedia

    INDEX
    Explanations

    performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mix
    -0.07
    ño
    -0.07
    .Summary
    -0.06
     Voter
    -0.06
    _FILE
    -0.06
     enrolled
    -0.06
     Rock
    -0.06
     mary
    -0.06
    夜
    -0.06
    新聞
    -0.06
    POSITIVE LOGITS
    ฎ
    0.07
    etine
    0.06
    .track
    0.06
     cheeks
    0.06
    startsWith
    0.06
    (ast
    0.06
     retal
    0.06
    life
    0.06
     plush
    0.06
     absurd
    0.06
    Act Density 0.012%

    No Known Activations