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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubator
    -0.09
     Plate
    -0.08
    ystone
    -0.08
     Batter
    -0.08
     barato
    -0.08
     <=",
    -0.08
     suaves
    -0.08
     propriétaires
    -0.07
     mmol
    -0.07
     Verein
    -0.07
    POSITIVE LOGITS
     excluding
    0.10
    Exclude
    0.09
    excluding
    0.08
     exclude
    0.08
     acting
    0.08
    exclude
    0.08
    .exclude
    0.08
    Excluded
    0.08
    aking
    0.08
     exclusion
    0.08
    Act Density 0.012%

    No Known Activations