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

    Neuronpedia

    INDEX
    Explanations

    figure references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addClass
    -0.07
    +
    -0.07
    θ
    -0.07
     Sche
    -0.07
    🐝
    -0.07
     equation
    -0.07
    <>();↵↵
    -0.07
     bodyParser
    -0.07
    то
    -0.07
    ⛈
    -0.07
    POSITIVE LOGITS
    (mat
    0.07
    (Process
    0.07
    约合
    0.07
     перев
    0.07
    찯
    0.07
     dejting
    0.07
     LAW
    0.06
     transforms
    0.06
     ROW
    0.06
    cohol
    0.06
    Act Density 0.006%

    No Known Activations