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
    (LayoutInflater
    -0.06
     Fine
    -0.06
     Find
    -0.06
     Fin
    -0.06
    h
    -0.06
    H
    -0.06
     tant
    -0.06
    HD
    -0.06
    粗
    -0.06
     ice
    -0.06
    POSITIVE LOGITS
    ">↵
    0.10
    ="/">↵
    0.08
    .descripcion
    0.07
    ...">↵
    0.07
     чемпион
    0.07
     ταιν
    0.07
    чення
    0.07
    '>↵
    0.07
    기에
    0.07
     Sext
    0.07
    Act Density 0.012%

    No Known Activations