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

    Neuronpedia

    INDEX
    Explanations

    letters/anagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    optim
    -0.07
    .YELLOW
    -0.07
    Visitor
    -0.07
    gid
    -0.06
     dvou
    -0.06
     Федера
    -0.06
    .Account
    -0.06
     πολυ
    -0.06
     Protected
    -0.06
    Append
    -0.06
    POSITIVE LOGITS
     Craig
    0.08
     quietly
    0.06
    ANE
    0.06
     lent
    0.06
    ελ
    0.06
    άρ
    0.06
    Greg
    0.06
    Craig
    0.06
    	endif
    0.06
     voy
    0.06
    Act Density 0.008%

    No Known Activations