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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Offers
    -0.07
    xFFFF
    -0.07
    bservable
    -0.07
    fills
    -0.06
     Republican
    -0.06
     مدیریت
    -0.06
     crack
    -0.06
     therap
    -0.06
     certificates
    -0.06
    ampion
    -0.06
    POSITIVE LOGITS
    (an
    0.06
    ="">
↵
    0.06
     organic
    0.06
     κ
    0.06
     проц
    0.06
    ToProps
    0.06
     začátku
    0.06
    Include
    0.06
    .INSTANCE
    0.06
    ?key
    0.06
    Act Density 0.015%

    No Known Activations