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

    Neuronpedia

    INDEX
    Explanations

    competitive offering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     خار
    0.47
    м
    0.46
    ।
    0.46
    <0x80>
    0.46
     PROJECT
    0.45
     be
    0.44
    ミ
    0.44
    م
    0.43
    ПР
    0.42
    ío
    0.42
    POSITIVE LOGITS
    羪
    0.47
     pann
    0.46
     pans
    0.46
     bây
    0.43
    ലെസ്
    0.42
     witchcraft
    0.42
     genres
    0.42
    丷
    0.41
     lymphomas
    0.41
     aquifers
    0.41
    Act Density 0.010%

    No Known Activations