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

    Neuronpedia

    INDEX
    Explanations

    Math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    from
    -0.07
     loading
    -0.07
     mb
    -0.07
     xrange
    -0.06
     대한
    -0.06
     biases
    -0.06
     кус
    -0.06
    -loading
    -0.06
    frame
    -0.06
    -order
    -0.06
    POSITIVE LOGITS
    řed
    0.08
    .setDescription
    0.06
    .req
    0.06
     prevented
    0.06
    anou
    0.06
    άρχ
    0.06
    rgctx
    0.06
    ＞
    0.06
    formace
    0.06
     Anat
    0.06
    Act Density 0.003%

    No Known Activations