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

    Neuronpedia

    INDEX
    Explanations

    Length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    談
    -0.07
    pu
    -0.07
    ]()↵
    -0.07
    possibly
    -0.07
    .");↵↵
    -0.07
    ึก
    -0.06
     ox
    -0.06
     hasn
    -0.06
    gender
    -0.06
     Cv
    -0.06
    POSITIVE LOGITS
     ميل
    0.06
     movable
    0.06
    می
    0.06
     zařízení
    0.06
     روان
    0.06
     Sequelize
    0.06
     FactoryGirl
    0.06
     Λα
    0.06
     OF
    0.06
     verdade
    0.06
    Act Density 0.029%

    No Known Activations