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

    Neuronpedia

    INDEX
    Explanations

    contractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坐落
    -0.08
    oningen
    -0.08
     forb
    -0.07
     nieu
    -0.07
    /↵↵↵↵
    -0.07
     bố
    -0.07
    â
    -0.07
     condo
    -0.07
    谢谢你
    -0.07
    _que
    -0.06
    POSITIVE LOGITS
    _LAYER
    0.07
    _PARAMETER
    0.07
    Bạn
    0.07
     этом
    0.07
    'M
    0.06
    _SERIAL
    0.06
    ，在
    0.06
    Instances
    0.06
    [ID
    0.06
    事を
    0.06
    Act Density 0.165%

    No Known Activations