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

    Neuronpedia

    INDEX
    Explanations

    expansion and related verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     גבוה
    0.44
    哉
    0.39
    בוה
    0.38
     totem
    0.35
     높은
    0.34
     brigades
    0.34
    ಿ
    0.33
     сово
    0.32
    ongan
    0.32
     Slayer
    0.32
    POSITIVE LOGITS
     expansion
    4.13
     expand
    4.06
     Expansion
    3.89
    Expansion
    3.84
     расши
    3.83
    expansion
    3.78
     Expand
    3.77
    Expand
    3.75
     expanding
    3.73
     expanded
    3.72
    Act Density 0.160%

    No Known Activations