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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'L
    -0.07
     Williamson
    -0.06
    تیب
    -0.06
     Pride
    -0.06
    FFE
    -0.06
    дж
    -0.06
    IRQ
    -0.06
    єте
    -0.06
     smashed
    -0.06
    cross
    -0.06
    POSITIVE LOGITS
    oblin
    0.08
     اب
    0.07
     minha
    0.06
     eskort
    0.06
    �
    0.06
     Quando
    0.06
     HVAC
    0.06
    achten
    0.06
     Schedule
    0.06
     тан
    0.06
    Act Density 0.003%

    No Known Activations