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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heller
    -0.07
    ocket
    -0.07
    fs
    -0.07
    -0.07
     columns
    -0.07
     slider
    -0.06
     Canadians
    -0.06
    irl
    -0.06
    Chocolate
    -0.06
     roof
    -0.06
    POSITIVE LOGITS
     Georg
    0.07
     ATI
    0.07
    Př
    0.06
    AndView
    0.06
    宽
    0.06
     Не
    0.06
    gın
    0.06
    Pa
    0.06
    InBackground
    0.06
     App
    0.06
    Act Density 0.006%

    No Known Activations