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

    Neuronpedia

    INDEX
    Explanations

    dates like sun, nov

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ito
    1.70
    $}
    1.66
    ^{
    1.56
    ''
    1.56
     ponctu
    1.48
    ′
    1.47
    𝐢
    1.47
     dese
    1.43
    𝐥
    1.42
    '"
    1.42
    POSITIVE LOGITS
    um
    1.89
     intervening
    1.72
    머
    1.65
     प्रभा
    1.65
     hvad
    1.65
     birefring
    1.60
    ע
    1.59
    bmi
    1.58
    ޘ
    1.58
    ്
    1.57
    Act Density 0.000%

    No Known Activations