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

    Neuronpedia

    INDEX
    Explanations

    care planning and provided

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ス
    1.05
    লা
    1.00
    ן
    0.98
    ời
    0.95
     océano
    0.95
    くらい
    0.95
     adaptés
    0.95
     Questo
    0.93
     adhipp
    0.91
     denounce
    0.91
    POSITIVE LOGITS
    n
    1.80
    ak
    1.53
    p
    1.53
    ig
    1.41
    x
    1.37
    f
    1.33
     in
    1.30
    在
    1.27
    us
    1.26
    care
    1.23
    Act Density 0.013%

    No Known Activations