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

    Neuronpedia

    INDEX
    Explanations

    violating safety guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    চার
    0.44
    似乎
    0.42
     COMPONENTS
    0.41
    தைய
    0.40
     TECHNIQUES
    0.40
    שה
    0.39
     элементов
    0.39
    ถูก
    0.38
    逐步
    0.38
    ASER
    0.38
    POSITIVE LOGITS
    atmos
    0.44
    ayt
    0.44
     którym
    0.41
     خدمت
    0.41
    遭受
    0.41
     pledging
    0.41
    customers
    0.40
     고객
    0.39
     وول
    0.39
     customers
    0.38
    Act Density 0.085%

    No Known Activations