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

    Neuronpedia

    INDEX
    Explanations

    powers and exponents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }_{-}\
    0.75
    }}_{
    0.75
     suburban
    0.71
     }_{
    0.69
    }_{
    0.68
    𝒟
    0.67
    🔜
    0.67
     ➤
    0.67
    inden
    0.66
     suburb
    0.66
    POSITIVE LOGITS
    ^
    3.65
     ^
    2.99
    <sup>
    2.90
    ^{
    2.60
    ^(
    2.59
    $^
    2.41
    ^^
    2.31
    .^
    2.29
     ^{
    2.27
    $^{
    2.27
    Act Density 0.172%

    No Known Activations