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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    在线咨询
    -0.08
    opolitan
    -0.07
     emploi
    -0.07
     Quarter
    -0.07
     commonly
    -0.07
     cùng
    -0.07
    .community
    -0.07
    widgets
    -0.07
     SHIPPING
    -0.06
    [word
    -0.06
    POSITIVE LOGITS
     burned
    0.07
    ).
    0.07
     adjusts
    0.07
     manipulated
    0.06
     marching
    0.06
    嘱
    0.06
    ㉱
    0.06
     responding
    0.06
    ()).
    0.06
    扶贫
    0.06
    Act Density 0.056%

    No Known Activations