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

    Neuronpedia

    INDEX
    Explanations

    word origins and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.79
    ific
    0.79
    lings
    0.79
    nesdays
    0.76
    キャリア
    0.71
    र्फ
    0.70
    ication
    0.70
    ivia
    0.70
     resolution
    0.70
    basics
    0.70
    POSITIVE LOGITS
     Fortnite
    0.82
     biblical
    0.79
     Bible
    0.79
     Razer
    0.78
     Biblical
    0.78
     fawn
    0.77
     Wordpress
    0.75
     Sodium
    0.75
     Oxford
    0.73
     raven
    0.73
    Act Density 0.012%

    No Known Activations