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

    Neuronpedia

    INDEX
    Explanations

    code syntax errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proficiency
    -0.07
     صرف
    -0.06
     hangi
    -0.06
    �
    -0.06
     متف
    -0.06
    Entities
    -0.06
     позволяет
    -0.06
    maal
    -0.06
     Companies
    -0.06
     movimiento
    -0.06
    POSITIVE LOGITS
     informing
    0.07
     Mafia
    0.07
     nour
    0.06
    :@{
    0.06
     dramatically
    0.06
     борь
    0.06
     :]
    0.06
     :]↵
    0.06
     Quân
    0.06
     Monitor
    0.06
    Act Density 0.016%

    No Known Activations