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

    Neuronpedia

    INDEX
    Explanations

    say phrase

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ически
    -0.07
    -analysis
    -0.07
    formulario
    -0.07
    KeyPress
    -0.07
    :block
    -0.07
     sided
    -0.06
     percentile
    -0.06
    ぜ
    -0.06
     filepath
    -0.06
     currentDate
    -0.06
    POSITIVE LOGITS
    _ROUTE
    0.06
     bq
    0.06
     suffer
    0.06
    ilyn
    0.06
     pl
    0.06
     expérience
    0.06
     functionality
    0.06
    翻
    0.06
     fell
    0.06
     ppm
    0.06
    Act Density 0.019%

    No Known Activations