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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purchase
    -0.07
     act
    -0.07
     Ruf
    -0.07
     kin
    -0.06
     tram
    -0.06
    _STENCIL
    -0.06
     boon
    -0.06
     додатков
    -0.06
    pen
    -0.06
     oxy
    -0.06
    POSITIVE LOGITS
    ۲۸
    0.06
    ("$.
    0.06
    €↵
    0.06
    مارات
    0.06
    lış
    0.06
    <br
    0.06
     Competitive
    0.06
    очка
    0.06
    ってる
    0.06
     ITE
    0.06
    Act Density 0.013%

    No Known Activations