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

    Neuronpedia

    INDEX
    Explanations

    Moshing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Перед
    -0.07
     accountant
    -0.07
    �
    -0.06
     Entities
    -0.06
     xảy
    -0.06
     bore
    -0.06
     irre
    -0.06
    Fund
    -0.06
     +#+#+#+
    -0.06
    POSITIVE LOGITS
    afari
    0.08
    /'↵
    0.07
     exhibiting
    0.07
    privation
    0.06
    unteer
    0.06
    ”:
    0.06
    iao
    0.06
     Конститу
    0.06
     kal
    0.06
     yiy
    0.06
    Act Density 0.001%

    No Known Activations