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

    Neuronpedia

    INDEX
    Explanations

    Finite fields

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hàng
    -0.07
     Level
    -0.07
     Erotik
    -0.07
     Explanation
    -0.07
    NoArgsConstructor
    -0.06
     Magazine
    -0.06
    系统
    -0.06
     Kumar
    -0.06
     maxLength
    -0.06
    -buy
    -0.06
    POSITIVE LOGITS
     drone
    0.07
    (express
    0.07
    $con
    0.07
    protect
    0.07
    (())↵
    0.06
     seeded
    0.06
    ?'
    0.06
    _reduce
    0.06
     (...)
    0.06
     Cartoon
    0.06
    Act Density 0.006%

    No Known Activations