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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ↵↵
    -0.07
    ัค
    -0.06
    /software
    -0.06
     کل
    -0.06
    _px
    -0.06
    cov
    -0.06
    кадем
    -0.06
    _BU
    -0.06
    etr
    -0.06
    HWND
    -0.06
    POSITIVE LOGITS
     bakery
    0.06
    마
    0.06
    мы
    0.06
    -с
    0.06
     Gür
    0.06
     geschichten
    0.06
    .',
    0.06
     WON
    0.06
     LLVM
    0.06
     Bett
    0.06
    Act Density 0.165%

    No Known Activations