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

    Neuronpedia

    INDEX
    Explanations

    much

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Straight
    -0.06
    (return
    -0.06
    Echo
    -0.06
     depot
    -0.06
    罚
    -0.06
     sessions
    -0.06
    氧
    -0.06
    Listen
    -0.06
    020
    -0.06
    arcer
    -0.06
    POSITIVE LOGITS
    'icon
    0.07
    >"
↵
    0.06
    )";
↵
    0.06
    ")]
↵
    0.06
    ,height
    0.06
    ITION
    0.06
    .rectangle
    0.06
    仪
    0.06
    loh
    0.05
     springfox
    0.05
    Act Density 0.038%

    No Known Activations