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

    Neuronpedia

    INDEX
    Explanations

    figura clave or important person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mandates
    0.44
     purview
    0.42
    mandatory
    0.40
    マジ
    0.40
    tweets
    0.39
    mapping
    0.39
    ipedia
    0.38
    明確
    0.38
    ρθ
    0.37
    ものが
    0.37
    POSITIVE LOGITS
    BeerItem
    0.46
     类
    0.44
    萫
    0.44
     Joko
    0.44
    Burst
    0.43
    Beans
    0.43
    ల్లి
    0.43
     উত্তেজিত
    0.43
     đóng
    0.43
     polynucle
    0.42
    Act Density 0.004%

    No Known Activations