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

    Neuronpedia

    INDEX
    Explanations

    file extensions for data and documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reserved
    0.75
     mosaics
    0.75
     converted
    0.73
    يديو
    0.72
    ভাস
    0.70
     mosaic
    0.69
     cast
    0.67
    كمال
    0.67
    蔵
    0.67
     next
    0.67
    POSITIVE LOGITS
    的任务
    0.90
     Snack
    0.90
     nar
    0.90
    的要求
    0.88
     cuyas
    0.87
    crisis
    0.84
    trivial
    0.84
    心理
    0.83
    进口
    0.83
     boycott
    0.82
    Act Density 0.075%

    No Known Activations