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

    Neuronpedia

    INDEX
    Explanations

    rules and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     collo
    0.75
    पीठ
    0.71
    事业单位
    0.71
     ṣe
    0.69
     vidéos
    0.68
    йович
    0.68
    aterials
    0.68
     performans
    0.68
     gah
    0.67
    縱
    0.67
    POSITIVE LOGITS
     rules
    5.84
     Rules
    5.44
     rule
    5.35
    Rules
    5.28
    rules
    5.16
    Rule
    4.79
     Rule
    4.77
    rule
    4.76
    规则
    4.75
     RULES
    4.70
    Act Density 0.472%

    No Known Activations