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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Event
    -0.07
     Cosmos
    -0.07
    ByteArray
    -0.07
     sina
    -0.06
     stil
    -0.06
    ив
    -0.06
     Details
    -0.06
    Dia
    -0.06
     na
    -0.06
     Bod
    -0.06
    POSITIVE LOGITS
    rays
    0.06
     syntax
    0.06
     playerId
    0.06
    _softc
    0.06
     slashes
    0.06
    mult
    0.06
    Marsh
    0.06
    Š
    0.06
     группы
    0.06
     wildfires
    0.06
    Act Density 0.094%

    No Known Activations