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

    Neuronpedia

    INDEX
    Explanations

    references to structural or hierarchical elements, particularly in discussions related to organization and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    stacking and piles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vician
    -0.37
     undated
    -0.36
     cuero
    -0.36
    íncipe
    -0.36
    Билгалдахарш
    -0.35
     concorso
    -0.34
     wę
    -0.34
    亿元
    -0.34
     tričko
    -0.34
     actores
    -0.34
    POSITIVE LOGITS
     stacking
    0.65
     piles
    0.62
     stack
    0.61
     towers
    0.59
     piled
    0.59
     stacks
    0.58
    Tower
    0.57
     tower
    0.57
     heap
    0.56
     piling
    0.56
    Act Density 0.099%

    No Known Activations