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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Enjoy
    -0.07
    —with
    -0.07
     patents
    -0.07
    шки
    -0.06
     を
    -0.06
     facing
    -0.06
     кур
    -0.06
     cheeks
    -0.06
    Glyph
    -0.06
    _places
    -0.06
    POSITIVE LOGITS
    syntax
    0.06
     mineral
    0.06
    United
    0.06
    [o
    0.06
    inent
    0.06
    Appending
    0.06
     geçir
    0.06
    autoreleasepool
    0.06
     Bağ
    0.06
    sys
    0.06
    Act Density 0.003%

    No Known Activations