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

    Neuronpedia

    INDEX
    Explanations

    words and phrases used to describe something

    oai_token-act-pair · gemini-2.0-flash

    Adverbs of degree

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intégré
    -0.45
    Newest
    -0.44
     newest
    -0.43
     waard
    -0.42
     للتو
    -0.42
    katapos
    -0.42
    sieme
    -0.41
    <<<<<<<<
    -0.41
     дописавши
    -0.40
     compréhen
    -0.40
    POSITIVE LOGITS
     mostly
    0.89
     Mainly
    0.86
     mainly
    0.85
    richTextPanel
    0.81
     gyhoeddwyd
    0.81
     Mostly
    0.78
     largely
    0.78
    Mainly
    0.77
    Mostly
    0.76
     more
    0.75
    Act Density 1.800%

    No Known Activations