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

    Neuronpedia

    INDEX
    Explanations

    metric and similarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ji
    0.40
     suasana
    0.39
    JI
    0.36
    scheme
    0.36
     moi
    0.35
     indignation
    0.35
    ឥត
    0.35
    jats
    0.34
    athu
    0.34
    jis
    0.34
    POSITIVE LOGITS
     근데
    0.42
     Revisited
    0.42
     服务
    0.42
     पार्ट्स
    0.41
     서비스
    0.41
     పరిశ
    0.40
    자로
    0.40
     услуг
    0.40
     பாக
    0.39
     ব্যাব
    0.39
    Act Density 0.000%

    No Known Activations