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

    Neuronpedia

    INDEX
    Explanations

    Table/List

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    calculator
    -0.08
     calculator
    -0.08
     calculators
    -0.08
     violently
    -0.08
     ال
    -0.08
     بچ
    -0.08
     ध्यान
    -0.07
     atenção
    -0.07
     plan
    -0.07
     secours
    -0.07
    POSITIVE LOGITS
     thrive
    0.08
    _transform
    0.08
    -operation
    0.08
    _operation
    0.07
    iknya
    0.07
    .commons
    0.07
     Bib
    0.07
    Eks
    0.07
    ીક
    0.07
    发展
    0.07
    Act Density 0.001%

    No Known Activations