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

    Neuronpedia

    INDEX
    Explanations

    commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GENER
    -0.07
    give
    -0.06
    ведите
    -0.06
    including
    -0.06
    SOURCE
    -0.06
    .INT
    -0.06
    貝
    -0.06
    ›
    -0.06
    Healthy
    -0.06
    uity
    -0.06
    POSITIVE LOGITS
    PACK
    0.06
     Formats
    0.06
     Customers
    0.06
    .platform
    0.06
    720
    0.06
     degradation
    0.06
    zeichnet
    0.06
     Useful
    0.06
    _SERVER
    0.06
    roma
    0.06
    Act Density 0.042%

    No Known Activations