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

    Neuronpedia

    INDEX
    Explanations

    functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _spawn
    -0.08
     united
    -0.08
     посад
    -0.07
    Mismatch
    -0.07
     cord
    -0.07
     avatars
    -0.07
    140
    -0.07
     ট
    -0.07
     оплач
    -0.07
     بطاقة
    -0.07
    POSITIVE LOGITS
     decreasing
    0.16
     increasing
    0.14
     monoton
    0.14
     decrease
    0.14
     decreases
    0.14
     monot
    0.13
    走势
    0.13
    Increasing
    0.13
     trend
    0.13
     Increasing
    0.13
    Act Density 0.063%

    No Known Activations