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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yurt
    -0.06
     takes
    -0.06
     fist
    -0.06
    �
    -0.06
    cion
    -0.06
     チ
    -0.06
    čné
    -0.06
    PageRoute
    -0.06
     salah
    -0.06
     Мар
    -0.06
    POSITIVE LOGITS
    13
    0.07
    gorithms
    0.06
    ٨
    0.06
    testing
    0.06
    ivariate
    0.06
    mpl
    0.06
     brat
    0.06
    nowledge
    0.06
     Dhabi
    0.06
     выше
    0.06
    Act Density 0.165%

    No Known Activations