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

    Neuronpedia

    INDEX
    Explanations

    take it seriously

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ično
    0.62
    であり
    0.60
     然後
    0.59
    と同様
    0.58
     입니다
    0.57
    uję
    0.57
    続いて
    0.57
    으로부터
    0.57
     وهنا
    0.56
    odynam
    0.56
    POSITIVE LOGITS
     Honda
    0.71
     tipos
    0.68
     Samsung
    0.68
     WWE
    0.66
     Beethoven
    0.65
    Samsung
    0.62
     What
    0.61
     Godzilla
    0.61
     Yamaha
    0.60
     nike
    0.60
    Act Density 0.000%

    No Known Activations