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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.69
     GenerationType
    -0.65
     فريبيس
    -0.64
    AddHtmlAttribute
    -0.62
    saraba
    -0.61
     utafitiHapana
    -0.60
    SupportActionBar
    -0.60
    MessageTagHelper
    -0.59
    PreferredItem
    -0.59
    DeleteBehavior
    -0.59
    POSITIVE LOGITS
     topic
    0.76
     that
    0.71
     the
    0.71
     subject
    0.66
    topic
    0.63
     sujets
    0.59
     Topic
    0.58
    ides
    0.56
     temáticas
    0.56
    .
    0.56
    Act Density 0.023%

    No Known Activations