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

    Neuronpedia

    INDEX
    Explanations

    spirit especially take hunters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.34
     a
    0.33
    sides
    0.29
    dados
    0.29
    soldiers
    0.29
    dach
    0.29
    muster
    0.28
    assem
    0.28
    μος
    0.28
    dependencies
    0.27
    POSITIVE LOGITS
    ਗ
    0.37
    те
    0.33
    クラ
    0.33
    タ
    0.32
    پ
    0.32
    ்ட்
    0.31
    専門
    0.30
     มา
    0.30
    .。
    0.30
     elétrica
    0.29
    Act Density 0.002%

    No Known Activations