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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elements
    -0.08
     Ils
    -0.07
    嶲
    -0.07
    %">
    -0.07
    ࠓ
    -0.07
    */↵
    -0.06
     werden
    -0.06
     />,↵
    -0.06
     mosque
    -0.06
     Charity
    -0.06
    POSITIVE LOGITS
     grandparents
    0.07
     Jim
    0.07
     Stretch
    0.07
    锶
    0.07
    古老
    0.07
     blanc
    0.06
     HIS
    0.06
    鄜
    0.06
     mrb
    0.06
     tricky
    0.06
    Act Density 0.064%

    No Known Activations