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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sigma
    -0.07
     shape
    -0.06
    UPS
    -0.06
    _path
    -0.06
     oxide
    -0.06
     Prevention
    -0.06
    Sigma
    -0.06
    .Deserialize
    -0.06
    .Double
    -0.06
    .Len
    -0.06
    POSITIVE LOGITS
    ());↵↵↵
    0.08
     Fresno
    0.07
     Sequelize
    0.07
     batting
    0.07
    {↵↵↵
    0.06
    ();↵↵↵↵
    0.06
        ↵    ↵
    0.06
     pres
    0.06
     titulo
    0.06
    ";↵↵↵
    0.06
    Act Density 0.002%

    No Known Activations