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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "?>↵
    -0.08
    adele
    -0.07
     Đức
    -0.07
     thôn
    -0.07
    ức
    -0.07
     Photon
    -0.06
     fred
    -0.06
     hinter
    -0.06
     derived
    -0.06
    ITED
    -0.06
    POSITIVE LOGITS
     çalışmalar
    0.07
     Tanner
    0.06
    xFFFFFFFF
    0.06
    (points
    0.06
    _GT
    0.06
    tm
    0.06
    _Ch
    0.06
     Flying
    0.06
    _bo
    0.06
     Hispanic
    0.06
    Act Density 0.028%

    No Known Activations