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

    Neuronpedia

    INDEX
    Explanations

    trace your, Media Engagement, lacked ambition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Forbes
    0.45
     weren
    0.44
     were
    0.43
    ket
    0.43
     apos
    0.42
     omkring
    0.42
     lng
    0.42
     estrada
    0.41
     Pistol
    0.41
     ha
    0.40
    POSITIVE LOGITS
    柟
    0.47
    ํานวน
    0.45
    堕
    0.44
    வா
    0.43
    руд
    0.42
    らく
    0.42
    ร
    0.42
    යන්
    0.41
    ೋತಿ
    0.41
     rapidement
    0.41
    Act Density 0.005%

    No Known Activations