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

    Neuronpedia

    INDEX
    Explanations

    executes compensating transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '
    0.37
     forex
    0.36
    '!
    0.34
     connected
    0.33
     f
    0.33
     rewards
    0.32
     tool
    0.32
     -
    0.31
     educational
    0.30
    !'
    0.30
    POSITIVE LOGITS
    그러나
    0.38
    ◤
    0.32
    ласти
    0.31
    ≡
    0.31
    ệt
    0.30
    リスト
    0.30
    ρι
    0.30
    根據
    0.30
    бля
    0.30
    ᱒
    0.29
    Act Density 0.000%

    No Known Activations