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

    Neuronpedia

    INDEX
    Explanations

    organizations and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     affluent
    0.81
     Ministério
    0.80
    ్‌
    0.79
     reprieve
    0.78
    น้อง
    0.77
     Ebola
    0.76
     prestigious
    0.76
     São
    0.76
     aspiring
    0.76
     Ocean
    0.75
    POSITIVE LOGITS
    hello
    0.77
    Constr
    0.75
     sommige
    0.75
     codimension
    0.75
    lemon
    0.75
    ContextCompat
    0.74
    ui
    0.74
     увидел
    0.74
     तत्वों
    0.74
    Contents
    0.74
    Act Density 0.177%

    No Known Activations