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

    Neuronpedia

    INDEX
    Explanations

    would you like more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உங்களுக்கு
    0.49
     contigo
    0.48
     ਤੁ
    0.47
     तुम्हाला
    0.46
    为你
    0.46
     మీకు
    0.46
     ਤੁਹਾ
    0.46
     आपसे
    0.45
    अव
    0.45
     vostri
    0.45
    POSITIVE LOGITS
     learn
    0.44
     truly
    0.44
     explore
    0.42
     any
    0.42
    eren
    0.42
     purge
    0.41
     attempts
    0.40
    ola
    0.38
     greatest
    0.38
     import
    0.38
    Act Density 0.001%

    No Known Activations