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

    Neuronpedia

    INDEX
    Explanations

    yard work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \(
    2.90
    \<
    2.89
     dabb
    2.88
    ѕ
    2.85
    jenigen
    2.81
    ℓ
    2.80
    ंबई
    2.79
     ομά
    2.78
    giene
    2.76
     Благодаря
    2.68
    POSITIVE LOGITS
    ل
    3.88
     putea
    2.95
    ル
    2.93
    愎
    2.91
    goed
    2.83
    й
    2.77
    n
    2.74
     paymentRequest
    2.63
    おく
    2.59
     vys
    2.56
    Act Density 0.004%

    No Known Activations