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

    Neuronpedia

    INDEX
    Explanations

    cutting ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exem
    0.44
    wek
    0.43
    یم
    0.41
    یس
    0.38
    umbuhan
    0.38
    жного
    0.38
    ឈ្ម
    0.38
     locus
    0.37
    等が
    0.37
    ᓇ
    0.37
    POSITIVE LOGITS
     Fragments
    0.73
     fragments
    0.67
    碎
    0.67
     fragmented
    0.67
     фраг
    0.66
    碎片
    0.64
     Fragment
    0.63
    Fragments
    0.62
    fragments
    0.62
    Fragment
    0.61
    Act Density 0.058%

    No Known Activations