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

    Neuronpedia

    INDEX
    Explanations

    military groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    1.18
     labios
    0.94
    arım
    0.94
    mike
    0.93
     cleaved
    0.93
     facere
    0.93
    mite
    0.92
    maks
    0.89
    mén
    0.88
    ean
    0.88
    POSITIVE LOGITS
    ✓
    1.09
    1.00
    ă
    0.99
    ।
    0.97
    ﺍ
    0.96
    ᚕ
    0.95
    [\
    0.95
    ๗
    0.93
    󰡔
    0.93
    ない
    0.92
    Act Density 0.005%

    No Known Activations