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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    جي
    -0.07
    illa
    -0.06
    _mc
    -0.06
    ант
    -0.06
    .HttpContext
    -0.06
    Memory
    -0.06
    ينية
    -0.06
    房屋
    -0.06
     clergy
    -0.06
    .nio
    -0.06
    POSITIVE LOGITS
    :)↵
    0.07
    safe
    0.07
     év
    0.07
     />)↵
    0.06
     sacr
    0.06
     �
    0.06
     польз
    0.06
     tent
    0.06
     demonstr
    0.06
     stalk
    0.06
    Act Density 0.053%

    No Known Activations