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

    Neuronpedia

    INDEX
    Explanations

    iterating through structures or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     roaming
    0.51
     roam
    0.43
     strolling
    0.43
     roving
    0.41
     पहल
    0.41
     wandering
    0.41
     funcionamiento
    0.40
     marched
    0.38
     ভুগ
    0.38
     struggles
    0.37
    POSITIVE LOGITS
     sequentially
    0.64
     collecting
    0.63
     picking
    0.59
     toward
    0.59
    寻找
    0.59
     until
    0.58
     faster
    0.58
     menuju
    0.58
     undetected
    0.58
     unnoticed
    0.57
    Act Density 0.046%

    No Known Activations