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

    Neuronpedia

    INDEX
    Explanations

    publications and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     daytime
    0.46
     Kardashians
    0.41
     Kardashian
    0.37
    immersive
    0.37
     ESPN
    0.37
     Daytime
    0.37
     stake
    0.37
     Matt
    0.37
     composing
    0.36
     Daily
    0.35
    POSITIVE LOGITS
    EDITORIAL
    0.81
    Editorial
    0.73
     Editorial
    0.73
     editorials
    0.72
    articles
    0.70
     articles
    0.70
     editorial
    0.68
     статей
    0.64
    editorial
    0.63
    Articles
    0.61
    Act Density 0.001%

    No Known Activations