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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dah
    -0.07
    enan
    -0.07
    为例
    -0.07
     вли
    -0.07
     Democratic
    -0.07
    议论
    -0.07
    &eacute
    -0.07
     negotiating
    -0.06
    零碎
    -0.06
    鳛
    -0.06
    POSITIVE LOGITS
    营
    0.08
     princípio
    0.08
    ี้
    0.07
    بين
    0.07
    .Pass
    0.07
    uras
    0.07
    >(
    0.06
    실
    0.06
     il
    0.06
    巴黎
    0.06
    Act Density 0.037%

    No Known Activations