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
     Barg
    -0.08
     Dong
    -0.08
     Berk
    -0.08
    休
    -0.08
     Rad
    -0.07
     Song
    -0.07
     Rot
    -0.07
     Yan
    -0.07
    Kom
    -0.07
    Tab
    -0.07
    POSITIVE LOGITS
     �
    0.07
    ("\\
    0.07
     '\\'
    0.07
     оказ
    0.07
    will
    0.07
    ABCDEFGHI
    0.06
    ":↵↵
    0.06
    _ex
    0.06
    .localizedDescription
    0.06
    .OUT
    0.06
    Act Density 0.006%

    No Known Activations