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

    Neuronpedia

    INDEX
    Explanations

    -driven

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     началь
    -0.07
     departamento
    -0.07
     Usuarios
    -0.06
     голови
    -0.06
     //-
    -0.06
     ساختمان
    -0.06
    ules
    -0.06
     cooking
    -0.06
     xyz
    -0.06
    _parents
    -0.06
    POSITIVE LOGITS
    Driven
    0.10
    -driven
    0.09
    orderId
    0.07
     driven
    0.07
     churn
    0.07
     чуть
    0.06
     كن
    0.06
    _plan
    0.06
    Drive
    0.06
     Protein
    0.06
    Act Density 0.004%

    No Known Activations