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

    Neuronpedia

    INDEX
    Explanations

    M

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isel
    -0.07
     ash
    -0.07
    打了
    -0.07
    eks
    -0.07
     modele
    -0.06
    ighet
    -0.06
     dated
    -0.06
     Budget
    -0.06
    KEN
    -0.06
    Updated
    -0.06
    POSITIVE LOGITS
     projection
    0.07
     Prediction
    0.07
    预测
    0.07
    目睹
    0.07
    プロジェクト
    0.07
    竹
    0.07
     joystick
    0.07
    projectId
    0.06
    โลก
    0.06
    睄
    0.06
    Act Density 0.002%

    No Known Activations