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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    这般
    -0.08
    lung
    -0.08
    .coll
    -0.07
    Desk
    -0.07
    一脸
    -0.07
    fmt
    -0.07
     fusion
    -0.06
     Transit
    -0.06
    BorderStyle
    -0.06
    ственные
    -0.06
    POSITIVE LOGITS
    迹象
    0.07
     Mod
    0.07
    firefox
    0.07
    計劃
    0.07
    Lord
    0.07
     Saf
    0.07
    wid
    0.06
     Force
    0.06
    ]))
↵
    0.06
     }}>↵
    0.06
    Act Density 0.001%

    No Known Activations