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

    Neuronpedia

    INDEX
    Explanations

    then, ask questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    észeti
    0.45
    entions
    0.43
    ꯑ
    0.40
    arrêter
    0.40
    ólogos
    0.40
    이
    0.40
    elems
    0.39
    대한
    0.39
     দিল্লির
    0.39
    ješ
    0.39
    POSITIVE LOGITS
     SS
    0.53
     TS
    0.50
     ECB
    0.50
     ES
    0.50
     Savior
    0.50
     TC
    0.47
     neutral
    0.47
     trauma
    0.46
     Kush
    0.46
     MTB
    0.46
    Act Density 0.003%

    No Known Activations