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

    Neuronpedia

    INDEX
    Explanations

    found

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     christmas
    -0.07
     fos
    -0.06
    AREA
    -0.06
     περ
    -0.06
    .%
    -0.06
    |%
    -0.06
     amounted
    -0.06
    스타
    -0.06
     دانشجوی
    -0.06
    esc
    -0.06
    POSITIVE LOGITS
     worth
    0.07
    ной
    0.06
    (itr
    0.06
     been
    0.06
    иной
    0.06
    вано
    0.06
     اینکه
    0.06
     STDCALL
    0.06
     другими
    0.06
     Initialized
    0.06
    Act Density 0.202%

    No Known Activations