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

    Neuronpedia

    INDEX
    Explanations

    capturing groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تجمع
    0.45
    ressione
    0.44
    filter
    0.38
    expressions
    0.37
    डून
    0.36
    过滤
    0.36
     भास्कर
    0.36
    waitForIdleSync
    0.35
     भाजी
    0.35
     greatly
    0.35
    POSITIVE LOGITS
     subgroups
    0.53
     captured
    0.49
     ditemukan
    0.48
     subgroup
    0.47
    Captured
    0.47
     Captured
    0.45
     grupy
    0.45
     районов
    0.45
     abducted
    0.42
    gefunden
    0.42
    Act Density 0.026%

    No Known Activations