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

    Neuronpedia

    INDEX
    Explanations

    another one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endous
    0.72
    라는
    0.72
    ခြေ
    0.72
     această
    0.72
     ayrıca
    0.68
    ృత
    0.66
    undaki
    0.65
    詳しい
    0.65
     außerdem
    0.64
     என்ற
    0.64
    POSITIVE LOGITS
     ones
    5.15
     Ones
    3.50
     quelli
    3.37
    ones
    3.08
     ceux
    3.02
     celles
    2.81
     celui
    2.66
     others
    2.60
     one
    2.54
     those
    2.53
    Act Density 1.867%

    No Known Activations