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

    Neuronpedia

    INDEX
    Explanations

    a WSGI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dobl
    0.52
     eje
    0.49
    clam
    0.46
    artige
    0.45
     autént
    0.44
     giảng
    0.44
     amid
    0.44
     más
    0.43
     anod
    0.43
     appell
    0.42
    POSITIVE LOGITS
    Customers
    0.53
    To
    0.52
     We
    0.52
     They
    0.51
    Manager
    0.50
    Customer
    0.50
     It
    0.49
     quarterly
    0.49
    Vacuum
    0.48
     To
    0.47
    Act Density 0.000%

    No Known Activations