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

    Neuronpedia

    INDEX
    Explanations

    blocking/plugging/jamming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alus
    -0.06
    123
    -0.06
     zdroj
    -0.06
    point
    -0.06
    	ax
    -0.06
     reliably
    -0.06
     mặt
    -0.06
    (th
    -0.06
     lust
    -0.06
     goes
    -0.06
    POSITIVE LOGITS
    방송
    0.06
    اصر
    0.06
     افزایش
    0.06
     asiat
    0.06
    avez
    0.06
     acquaint
    0.06
     easing
    0.06
    Difficulty
    0.06
    gebra
    0.06
    =false
    0.06
    Act Density 0.107%

    No Known Activations