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

    Neuronpedia

    INDEX
    Explanations

    nearing completion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Herr
    -0.07
     Από
    -0.06
     подаль
    -0.06
    str
    -0.06
    ście
    -0.06
    及其
    -0.06
     fract
    -0.06
    Choices
    -0.06
    府
    -0.06
    Todd
    -0.06
    POSITIVE LOGITS
    ulsion
    0.07
    userRepository
    0.07
    iddles
    0.06
     Buk
    0.06
    ELS
    0.06
     (%)
    0.06
    ök
    0.06
     Ethiopia
    0.06
     sạn
    0.06
     kültür
    0.06
    Act Density 0.110%

    No Known Activations