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

    Neuronpedia

    INDEX
    Explanations

    language and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uninsured
    0.40
     theses
    0.38
     uter
    0.37
     gloria
    0.37
     Think
    0.37
     insulin
    0.36
     MC
    0.36
     mba
    0.36
     greg
    0.36
     rig
    0.35
    POSITIVE LOGITS
    сто
    0.38
     نفسها
    0.37
    헉
    0.37
     связана
    0.36
    Bird
    0.36
    战士
    0.35
     మారింది
    0.35
     czynności
    0.35
     வணக்கம்
    0.35
     छोटा
    0.35
    Act Density 0.000%

    No Known Activations