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

    Neuronpedia

    INDEX
    Explanations

    C++ libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _AGENT
    -0.09
     holog
    -0.09
    …………………………………………
    -0.08
     свид
    -0.08
     maxim
    -0.08
    ICES
    -0.08
    .Driver
    -0.08
    …….
    -0.08
     Genève
    -0.08
     Jessica
    -0.08
    POSITIVE LOGITS
    库
    0.09
    erc
    0.08
    -Core
    0.08
    -core
    0.08
    deprecated
    0.08
    Contains
    0.08
    包含
    0.08
     Contains
    0.08
    Core
    0.08
    中的
    0.08
    Act Density 0.019%

    No Known Activations