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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     지원
    -0.07
     Onc
    -0.07
    餐
    -0.07
     Poker
    -0.07
    autorelease
    -0.06
    Players
    -0.06
     Trick
    -0.06
    ีเด
    -0.06
     horrific
    -0.06
    	begin
    -0.06
    POSITIVE LOGITS
     +↵
    0.07
     бол
    0.07
    $
    0.06
    utely
    0.06
    eldon
    0.06
    AAAA
    0.06
     легко
    0.06
    setFlash
    0.06
    �
    0.06
     gint
    0.06
    Act Density 0.232%

    No Known Activations