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

    Neuronpedia

    INDEX
    Explanations

    de acuerdo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    な
    0.86
    ℗
    0.86
    에
    0.85
    ف
    0.83
     માટે
    0.82
     हेतु
    0.80
    方法
    0.80
     التقل
    0.78
    のような
    0.75
    アカウント
    0.74
    POSITIVE LOGITS
     acuerdo
    1.23
     origen
    1.14
     repente
    1.13
     riferimento
    1.13
     acordo
    1.12
     interesse
    1.10
     ensue
    1.08
     inmediato
    1.07
     sorts
    1.04
     facto
    1.04
    Act Density 0.040%

    No Known Activations