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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GPL
    -0.08
     مطالعه
    -0.07
    stacle
    -0.07
     fermented
    -0.07
    _male
    -0.07
    _lambda
    -0.07
    락
    -0.06
     missing
    -0.06
     malaria
    -0.06
     lambda
    -0.06
    POSITIVE LOGITS
    τζ
    0.07
    .ro
    0.06
    [row
    0.06
     Rapids
    0.06
    .:.:.
    0.06
     대해
    0.06
    .DataContext
    0.05
     utilis
    0.05
    ном
    0.05
    /commons
    0.05
    Act Density 0.141%

    No Known Activations