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

    Neuronpedia

    INDEX
    Explanations

    treating like family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -1.70
     or
    -1.47
     for
    -1.11
     alcune
    -1.10
     برخی
    -0.95
    の影響
    -0.95
     tartış
    -0.91
    InsertCommand
    -0.89
     dilaksanakan
    -0.88
     results
    -0.88
    POSITIVE LOGITS
    település
    1.21
     رغم
    1.11
    realme
    1.08
     voltak
    1.07
    羟
    1.06
    étaient
    1.04
    前回の
    1.03
    உ
    1.02
    Dès
    1.01
     épreuve
    1.01
    Act Density 0.005%

    No Known Activations