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

    Neuronpedia

    INDEX
    Explanations

    Data categories/types

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rowling
    -0.08
     comodidad
    -0.08
    XML
    -0.08
    _XML
    -0.08
    (row
    -0.08
    _ELEMENTS
    -0.08
    NSArray
    -0.08
    Rows
    -0.08
    På
    -0.08
     sweating
    -0.08
    POSITIVE LOGITS
     General
    0.16
    General
    0.14
     Currency
    0.14
     currency
    0.12
    _currency
    0.12
    Currency
    0.12
    general
    0.12
    .General
    0.12
     GENERAL
    0.12
    _general
    0.12
    Act Density 0.006%

    No Known Activations