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

    Neuronpedia

    INDEX
    Explanations

    place names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diagonalization
    0.86
     도형
    0.76
    Ꮸ
    0.73
     polytopes
    0.72
    ীম
    0.68
    АР
    0.66
    アクション
    0.66
     GoObject
    0.66
     diagonalizable
    0.66
    ил
    0.65
    POSITIVE LOGITS
    !
    0.75
    仙台
    0.68
     Mariners
    0.66
     Ou
    0.61
     Até
    0.58
     όπως
    0.57
     Comme
    0.57
    !</
    0.57
     Icelandic
    0.56
     textile
    0.55
    Act Density 0.009%

    No Known Activations