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

    Neuronpedia

    INDEX
    Explanations

    Periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ış
    -0.08
     thì
    -0.07
    ༕
    -0.07
     đường
    -0.07
    itez
    -0.06
    Ņ
    -0.06
    _MetaData
    -0.06
    etes
    -0.06
     duże
    -0.06
     intéress
    -0.06
    POSITIVE LOGITS
     bland
    0.07
    嗡
    0.07
    _loan
    0.07
    _render
    0.07
    .gender
    0.07
    �
    0.07
    其余
    0.07
     builtin
    0.07
    -serif
    0.06
     LOWER
    0.06
    Act Density 0.068%

    No Known Activations