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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lixo
    -0.09
     adequ
    -0.08
     rins
    -0.08
     otim
    -0.08
    clos
    -0.08
     disinfect
    -0.08
    -0.08
     maximizing
    -0.08
     positively
    -0.08
     skincare
    -0.07
    POSITIVE LOGITS
     ungewöhn
    0.10
     irrational
    0.10
     پیچ
    0.10
     необы
    0.09
    复杂
    0.09
     unconventional
    0.09
     unusual
    0.09
     неож
    0.09
     afwijk
    0.09
     Byzantine
    0.09
    Act Density 0.004%
    No Known Activations