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

    Neuronpedia

    INDEX
    Explanations

    autos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STILL
    -0.08
     रन
    -0.06
     summ
    -0.06
    respect
    -0.06
     still
    -0.06
     rat
    -0.06
     Бор
    -0.06
     tribute
    -0.06
     Mc
    -0.06
     NV
    -0.06
    POSITIVE LOGITS
    icient
    0.07
    STRUCT
    0.06
     jednodu
    0.06
     слишком
    0.06
    čemž
    0.06
    Communication
    0.06
    圖
    0.06
    interested
    0.06
    (xhr
    0.06
    ican
    0.06
    Act Density 0.061%

    No Known Activations