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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "le-" in words

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

    leeway, leached, leeches, leucine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.61
     ainfi
    -0.61
    __*/
    -0.61
    wahati
    -0.58
    Архівовано
    -0.55
    팎
    -0.55
     Gegenteil
    -0.54
     يتيمه
    -0.54
    HasColumnType
    -0.53
     desmotivaciones
    -0.52
    POSITIVE LOGITS
     le
    1.72
     LE
    1.08
    Le
    1.05
     Le
    1.02
    LE
    0.96
    le
    0.92
    Lea
    0.86
     Lea
    0.84
     Lec
    0.80
     lea
    0.79
    Act Density 0.020%

    No Known Activations