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

    Neuronpedia

    INDEX
    Explanations

    advice and related phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scol
    0.55
     সঠিক
    0.54
     વેબસ
    0.52
     सर्ट
    0.51
     profesores
    0.50
     contrat
    0.49
     технологии
    0.47
    Js
    0.47
     plagiarism
    0.47
    Kons
    0.47
    POSITIVE LOGITS
    ست
    0.77
    خ
    0.73
    ,
    0.68
    ك
    0.65
    ەر
    0.59
    یت
    0.57
    p
    0.53
    ль
    0.52
    的
    0.52
    を聞
    0.51
    Act Density 0.010%

    No Known Activations