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

    Neuronpedia

    INDEX
    Explanations

    scientific references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    述
    -0.06
    现代
    -0.06
     posterior
    -0.06
     exiting
    -0.06
    angles
    -0.06
     Frau
    -0.06
     polymer
    -0.06
    <dynamic
    -0.06
     trúc
    -0.06
     двиг
    -0.06
    POSITIVE LOGITS
     ){↵
    0.07
     allure
    0.07
    .so
    0.07
    ::::::
    0.07
    '][
    0.06
    -devel
    0.06
    Κ
    0.06
    .Immutable
    0.06
     (!
    0.06
    !!!
    0.06
    Act Density 0.007%

    No Known Activations