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

    Neuronpedia

    INDEX
    Explanations

    thin layers/interfaces

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exao
    -0.07
     terra
    -0.06
    website
    -0.06
    technical
    -0.06
    svn
    -0.06
    ể
    -0.06
    scss
    -0.06
     CPU
    -0.06
     refin
    -0.06
     organizace
    -0.06
    POSITIVE LOGITS
     factors
    0.06
    _charge
    0.06
    ~":"
    0.06
    rtle
    0.06
     Steele
    0.06
    amm
    0.06
    .forName
    0.06
     uuid
    0.06
     亚
    0.06
     fast
    0.06
    Act Density 0.032%

    No Known Activations