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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     budeme
    -0.07
     başına
    -0.06
    DOMNode
    -0.06
    .FullName
    -0.06
     Bits
    -0.06
    	fd
    -0.06
     Ст
    -0.06
     olanak
    -0.06
     ^↵
    -0.06
     Αρ
    -0.06
    POSITIVE LOGITS
     synerg
    0.07
    将
    0.07
     quieter
    0.07
    IALOG
    0.06
     cường
    0.06
    업
    0.06
     lessons
    0.06
    yl
    0.06
    Hall
    0.06
     seats
    0.06
    Act Density 0.007%

    No Known Activations