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

    Neuronpedia

    INDEX
    Explanations

    seed and planting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    1.91
    cie
    1.77
     sebenarnya
    1.75
    ための
    1.65
    stration
    1.59
    möglich
    1.55
    eritud
    1.51
    ir
    1.49
    ے
    1.49
     זאת
    1.48
    POSITIVE LOGITS
     seeds
    1.66
     Seeds
    1.63
     huấn
    1.63
    ан
    1.47
    蛉
    1.47
     평
    1.46
    Seeds
    1.46
     fulfill
    1.45
    ৯
    1.43
    ром
    1.42
    Act Density 0.007%

    No Known Activations