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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WORDS
    -0.07
    280
    -0.06
    mma
    -0.06
    (simp
    -0.06
    -language
    -0.06
     scoff
    -0.06
    qw
    -0.06
    _movie
    -0.06
    各种
    -0.06
    lanır
    -0.06
    POSITIVE LOGITS
     AUT
    0.07
    ào
    0.07
     instant
    0.07
     uz
    0.06
     μετα
    0.06
    ٬
    0.06
    /********************************
    0.06
    testing
    0.06
    ?',↵
    0.06
     ua
    0.06
    Act Density 0.019%

    No Known Activations