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

    Neuronpedia

    INDEX
    Explanations

    mg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ull
    -0.07
     Zoo
    -0.07
    اول
    -0.06
    ustral
    -0.06
     kor
    -0.06
    ULL
    -0.06
    也是
    -0.06
     Behaviour
    -0.06
    aux
    -0.06
    all
    -0.06
    POSITIVE LOGITS
    mg
    0.10
     mg
    0.10
    -inf
    0.09
     mip
    0.08
     Mg
    0.07
     MG
    0.07
     Merc
    0.07
    iman
    0.06
     мг
    0.06
     produced
    0.06
    Act Density 0.006%

    No Known Activations