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

    Neuronpedia

    INDEX
    Explanations

    you don't have to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्टी
    0.78
     অভাব
    0.70
    Ste
    0.65
     unable
    0.64
     Inspe
    0.58
     inability
    0.58
    ब्दिक
    0.55
     Hagen
    0.55
    вичай
    0.54
     succ
    0.54
    POSITIVE LOGITS
    駱
    0.76
     Don
    0.75
    示范
    0.74
    isometric
    0.74
    Isometric
    0.73
     DON
    0.72
     needn
    0.71
    বঙ্গে
    0.71
    alisation
    0.71
     jederzeit
    0.70
    Act Density 0.054%

    No Known Activations