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

    Neuronpedia

    INDEX
    Explanations

    gaining attention or debate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tercih
    0.70
    ্শন
    0.66
    ഠ
    0.64
    advant
    0.63
     অক্ষম
    0.62
    iciency
    0.62
     yawning
    0.61
    임을
    0.61
    SIMPLEX
    0.61
     proficiency
    0.61
    POSITIVE LOGITS
     controversy
    1.53
     Controversy
    1.41
     debate
    1.30
     controversies
    1.27
     rumors
    1.21
     discussions
    1.17
     rumours
    1.16
     discussion
    1.15
    争议
    1.14
     rumores
    1.14
    Act Density 0.618%

    No Known Activations