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

    Neuronpedia

    INDEX
    Explanations

    emojis and playful expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.48
    ম
    0.48
     ऋ
    0.44
    鞍
    0.43
     auspices
    0.42
    合わせ
    0.42
     apportionment
    0.42
    㘿
    0.41
    참
    0.41
     最
    0.41
    POSITIVE LOGITS
     filtrar
    0.52
    过滤
    0.49
    Filtering
    0.48
     في
    0.45
     spada
    0.45
     محافظة
    0.45
     Rezept
    0.45
    Meyer
    0.44
     Qualitäts
    0.44
     பகுதியில்
    0.44
    Act Density 0.005%

    No Known Activations