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

    Neuronpedia

    INDEX
    Explanations

    win

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    null
    -0.07
     Declare
    -0.06
    Initializing
    -0.06
    막
    -0.06
    opoly
    -0.06
     Mitarbeiter
    -0.06
     sheds
    -0.06
     Piper
    -0.06
     cleanse
    -0.06
    herence
    -0.06
    POSITIVE LOGITS
     अल
    0.07
     ung
    0.07
     امیر
    0.07
    ;r
    0.07
    (di
    0.06
     engel
    0.06
    Christmas
    0.06
     Bow
    0.06
                
↵
    0.06
     diagon
    0.06
    Act Density 0.005%

    No Known Activations