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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cooperative
    -0.08
     Salisbury
    -0.08
     ప్రచ
    -0.08
     существует
    -0.07
     postoji
    -0.07
     gezin
    -0.07
    .quote
    -0.07
     Stamford
    -0.07
     agility
    -0.07
     arter
    -0.07
    POSITIVE LOGITS
     sección
    0.10
    SECTION
    0.08
    Section
    0.08
     section
    0.08
     sections
    0.08
    section
    0.08
    _section
    0.08
    �
    0.07
     SECTION
    0.07
    _settings
    0.07
    Act Density 0.007%

    No Known Activations