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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    逃
    -0.07
    心
    -0.07
    -content
    -0.07
    Federal
    -0.07
    ễn
    -0.07
     Hyundai
    -0.07
     hot
    -0.07
    >User
    -0.07
     Sens
    -0.06
    POSITIVE LOGITS
     Amendment
    0.09
    alom
    0.07
    al
    0.07
     voir
    0.07
    硪
    0.07
     Caleb
    0.07
     stato
    0.06
    各种各样
    0.06
     Languages
    0.06
    _reading
    0.06
    Act Density 0.022%

    No Known Activations