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

    Neuronpedia

    INDEX
    Explanations

    directory paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anivers
    0.70
     Sag
    0.69
     ϒ
    0.69
     Takeuchi
    0.69
    <h6>
    0.66
     Beziehungen
    0.66
     із
    0.65
     ＜
    0.65
     Espagne
    0.65
     Orders
    0.63
    POSITIVE LOGITS
     kurta
    0.82
     массы
    0.79
     seer
    0.79
     granola
    0.79
     turban
    0.79
     hearted
    0.78
     grail
    0.78
     naan
    0.78
     gravy
    0.77
    ೇಶ್
    0.77
    Act Density 0.001%

    No Known Activations