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

    Neuronpedia

    INDEX
    Explanations

    fragment or parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    substrate
    0.42
     自転車
    0.38
    сіб
    0.38
    Dirs
    0.38
    軹
    0.37
    赈
    0.37
     modelled
    0.37
     "@/
    0.37
    ន់
    0.36
    رمپ
    0.36
    POSITIVE LOGITS
     fragment
    2.20
     fragments
    2.16
     fragmentation
    2.00
     Fragment
    1.98
    fragment
    1.95
    Fragment
    1.89
     fragmented
    1.87
     Fragments
    1.85
     фраг
    1.84
    碎片
    1.84
    Act Density 0.008%

    No Known Activations