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

    Neuronpedia

    INDEX
    Explanations

    models and miniatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anotar
    0.78
    पोरेशन
    0.76
     kayıt
    0.74
     അറ
    0.74
     philosophie
    0.73
     Summar
    0.72
    怦
    0.71
    ダンス
    0.71
     বৃত্ত
    0.70
     confluent
    0.70
    POSITIVE LOGITS
    模型
    1.95
     miniatures
    1.93
     model
    1.90
     miniature
    1.89
     models
    1.86
    模型的
    1.78
     模型
    1.74
    的模型
    1.74
     Models
    1.73
    model
    1.72
    Act Density 0.145%

    No Known Activations