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

    Neuronpedia

    INDEX
    Explanations

    Understanding/knowing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Transformers
    -0.07
    hem
    -0.07
    361
    -0.06
     sealing
    -0.06
    享
    -0.06
     BX
    -0.06
    Timer
    -0.06
    brahim
    -0.06
     λ
    -0.06
    _positive
    -0.06
    POSITIVE LOGITS
    _subplot
    0.06
    ('\
    0.06
     completo
    0.06
    ocommerce
    0.06
     стат
    0.06
    /commons
    0.06
    _zoom
    0.06
     animations
    0.06
    ська
    0.06
    _ART
    0.05
    Act Density 0.122%

    No Known Activations