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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sublist
    -0.08
     bề
    -0.07
    iquer
    -0.07
    /filepath
    -0.07
     듯
    -0.06
    逃
    -0.06
     kıy
    -0.06
    President
    -0.06
     catchy
    -0.06
     dresser
    -0.06
    POSITIVE LOGITS
    เทศ
    0.07
     가입
    0.07
     طریق
    0.07
    wd
    0.06
    нений
    0.06
    ------------------------------------------------
    0.06
    с
    0.06
    ilage
    0.06
    /Graphics
    0.06
    ////////////////////////////////////////////////
    0.06
    Act Density 0.004%

    No Known Activations