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

    Neuronpedia

    INDEX
    Explanations

    coordinates and vertices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ignano
    0.43
     recognition
    0.39
     gels
    0.39
    ジェ
    0.38
     расстоя
    0.38
    ACKS
    0.38
     bhavanti
    0.38
     সাফল্যের
    0.38
     reconnu
    0.37
     deficiencies
    0.36
    POSITIVE LOGITS
    戻
    0.48
     关闭
    0.48
    边缘
    0.43
    顶部
    0.41
    🔊
    0.41
     حجت
    0.41
     topRight
    0.40
     वापस
    0.40
     `#
    0.40
     τύ
    0.40
    Act Density 0.026%

    No Known Activations