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

    Neuronpedia

    INDEX
    Explanations

    legal and compliance terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     magically
    1.02
     conquering
    1.02
     messed
    0.97
     playback
    0.97
     toppers
    0.96
     fluffy
    0.95
     hipster
    0.94
     sleek
    0.94
     DIY
    0.94
     amus
    0.94
    POSITIVE LOGITS
    Just
    0.65
     just
    0.60
     previa
    0.59
     مقرر
    0.59
     reiter
    0.57
     Just
    0.57
    рати
    0.55
     formal
    0.55
    gar
    0.51
     manifiesta
    0.50
    Act Density 0.144%

    No Known Activations