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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .track
    -0.07
     маш
    -0.07
    sts
    -0.07
    geb
    -0.06
    ators
    -0.06
    Leaders
    -0.06
    kB
    -0.06
    crawler
    -0.06
     supremacist
    -0.06
    疗
    -0.06
    POSITIVE LOGITS
     Som
    0.07
    getDoctrine
    0.07
    (Locale
    0.07
     д
    0.07
     Jaime
    0.07
     ↵        ↵
    0.06
     versatility
    0.06
     pyplot
    0.06
    &↵
    0.06
     :=↵
    0.06
    Act Density 0.009%

    No Known Activations