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

    Neuronpedia

    INDEX
    Explanations

    Braces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PHYS
    -0.07
     Reverse
    -0.06
     comparative
    -0.06
     Б
    -0.06
    ۲۴
    -0.06
     nossa
    -0.06
     عنه
    -0.06
    ocate
    -0.06
     NA
    -0.06
     Stevenson
    -0.06
    POSITIVE LOGITS
     getUsers
    0.07
    emet
    0.06
     jenter
    0.06
     corridor
    0.06
    gons
    0.06
    cosystem
    0.06
     envelop
    0.06
    nell
    0.06
    horia
    0.06
    ции
    0.06
    Act Density 0.004%

    No Known Activations