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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paz
    -0.07
     kadın
    -0.06
    eln
    -0.06
    tical
    -0.06
    allas
    -0.06
     آنان
    -0.06
     Я
    -0.06
    ВО
    -0.06
    —an
    -0.06
     лют
    -0.06
    POSITIVE LOGITS
    ูร
    0.07
    numberOf
    0.07
    .destroyAllWindows
    0.06
     sugars
    0.06
    ]")]↵
    0.06
     �
    0.06
     IRS
    0.06
     remodel
    0.06
     surviv
    0.06
     Hydro
    0.06
    Act Density 0.001%

    No Known Activations