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

    Neuronpedia

    INDEX
    Explanations

    structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fas
    -0.07
    /github
    -0.07
    .Method
    -0.06
     Barbar
    -0.06
    NotFound
    -0.06
    _python
    -0.06
    สต
    -0.06
    ա�
    -0.06
     Cyprus
    -0.06
    .hardware
    -0.06
    POSITIVE LOGITS
     tipping
    0.07
    ruise
    0.07
     Dorothy
    0.07
     beautiful
    0.06
    _short
    0.06
     grande
    0.06
     reproduced
    0.06
    ultiple
    0.06
     clique
    0.06
     Numerous
    0.06
    Act Density 0.005%

    No Known Activations