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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    üml
    -0.07
    /legal
    -0.07
     Bomb
    -0.06
    PA
    -0.06
    -CS
    -0.06
     Composition
    -0.06
    Rank
    -0.06
    ULE
    -0.06
    fragment
    -0.06
     fragment
    -0.06
    POSITIVE LOGITS
    (sockfd
    0.06
    Terrain
    0.06
    打开
    0.06
     indeed
    0.06
    (chart
    0.06
     мяг
    0.06
    ereum
    0.06
     initialState
    0.06
     pitched
    0.06
    lua
    0.06
    Act Density 0.003%

    No Known Activations