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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spinner
    -0.08
     innovation
    -0.07
     subsystem
    -0.06
     prize
    -0.06
     restricting
    -0.06
    },
    -0.06
     RCC
    -0.06
    $log
    -0.06
     ولد
    -0.06
    .startswith
    -0.06
    POSITIVE LOGITS
    GLenum
    0.07
     Κυ
    0.07
     etk
    0.06
    Backdrop
    0.06
     оди
    0.06
     ابت
    0.06
     Yue
    0.06
     Gü
    0.06
    λά
    0.06
     аром
    0.06
    Act Density 0.002%

    No Known Activations