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

    Neuronpedia

    INDEX
    Explanations

    task completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ajero
    0.36
    pcl
    0.35
     প্রচলিত
    0.35
    噪
    0.34
     pcl
    0.33
     coronal
    0.33
     Kalk
    0.32
     suppressor
    0.32
     calc
    0.32
     evoked
    0.31
    POSITIVE LOGITS
     completion
    2.00
    完成
    1.99
     completing
    1.84
     completed
    1.82
     Completion
    1.78
    Completion
    1.77
    completion
    1.75
     完成
    1.74
     완료
    1.72
    完成了
    1.70
    Act Density 0.052%

    No Known Activations