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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    913
    -0.07
    lu
    -0.07
     Yak
    -0.07
    airie
    -0.07
     ceremon
    -0.07
    alis
    -0.07
    Invest
    -0.06
     imp
    -0.06
    _Re
    -0.06
     Hier
    -0.06
    POSITIVE LOGITS
     vois
    0.07
     AssemblyCopyright
    0.06
     mặc
    0.06
    _Position
    0.06
    移到
    0.06
     đã
    0.06
     console
    0.06
     видов
    0.06
     pornstar
    0.06
     sofort
    0.06
    Act Density 0.016%

    No Known Activations