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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    иту
    -0.07
    _SCOPE
    -0.07
    SDL
    -0.06
    .quantity
    -0.06
    ']:
    -0.06
     Chargers
    -0.06
     cinemas
    -0.06
     specular
    -0.06
     Depot
    -0.06
    POSITIVE LOGITS
     são
    0.06
    overview
    0.06
     Can
    0.06
     excited
    0.06
     Convention
    0.06
     differ
    0.06
     afterward
    0.06
    Bo
    0.06
     proposition
    0.05
     comprise
    0.05
    Act Density 0.015%

    No Known Activations