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

    Neuronpedia

    INDEX
    Explanations

    SQL LIKE clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dividers
    0.44
     ascertained
    0.43
     andRow
    0.42
     মহিলার
    0.41
    下さい
    0.41
    ISPW
    0.40
     पुरस्कार
    0.40
    쌤
    0.40
     divider
    0.39
     divergents
    0.39
    POSITIVE LOGITS
     l
    0.44
     τη
    0.43
     Gator
    0.38
     che
    0.37
    旣
    0.37
     d
    0.37
     حتى
    0.36
     Sistema
    0.36
     dis
    0.35
     blot
    0.35
    Act Density 0.000%

    No Known Activations