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

    Neuronpedia

    INDEX
    Explanations

    say "EITHER"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     д
    -0.09
    돤
    -0.07
     Tr
    -0.07
     Peach
    -0.07
    /V
    -0.07
    Kr
    -0.07
    ARD
    -0.07
     Дж
    -0.07
     Ef
    -0.07
     Cad
    -0.07
    POSITIVE LOGITS
     ”↵↵
    0.07
    '↵↵
    0.06
    止损
    0.06
     Buying
    0.06
    ificate
    0.06
    ונו
    0.06
     placer
    0.06
    ylvania
    0.06
    ♉
    0.06
    stands
    0.06
    Act Density 0.000%

    No Known Activations