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

    Neuronpedia

    INDEX
    Explanations

    test/survey validation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Д
    -0.07
     employee
    -0.07
     employees
    -0.07
     plot
    -0.07
    也
    -0.07
     chapters
    -0.06
    Rating
    -0.06
     pallet
    -0.06
     accurate
    -0.06
     mí
    -0.06
    POSITIVE LOGITS
     olmaz
    0.08
    _avail
    0.07
    .rank
    0.07
     Himal
    0.07
    .lastIndexOf
    0.07
    InnerHTML
    0.07
     различных
    0.06
    .Scroll
    0.06
    .div
    0.06
    ğit
    0.06
    Act Density 0.062%

    No Known Activations