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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ourtney
    0.44
    정한
    0.43
     are
    0.39
    ড়ন
    0.39
     Instances
    0.39
     Amin
    0.38
    创建一个
    0.38
    ished
    0.38
    eliers
    0.38
     percent
    0.38
    POSITIVE LOGITS
     hommage
    0.48
    を備
    0.48
     poesia
    0.45
     τησ
    0.45
     coopération
    0.45
     hätte
    0.44
    スキー
    0.43
     pegatina
    0.43
    Deux
    0.43
     équipé
    0.43
    Act Density 0.006%

    No Known Activations