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

    Neuronpedia

    INDEX
    Explanations

    thank you for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    YES
    0.45
     کمک
    0.45
     हाय
    0.43
     HEALTH
    0.41
    我会
    0.41
     مساعد
    0.40
    新建
    0.40
    ogenes
    0.40
     असल्यास
    0.40
     ആരോഗ്യ
    0.39
    POSITIVE LOGITS
     Cours
    0.42
    監視
    0.38
     frit
    0.37
     contamin
    0.37
     contaminate
    0.37
     ,
    0.36
     That
    0.35
    とする
    0.35
     invaded
    0.35
     käyttää
    0.35
    Act Density 0.001%

    No Known Activations