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

    Neuronpedia

    INDEX
    Explanations

    Al Jazeera news links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    英国
    0.46
     فور
    0.43
    Model
    0.40
    德国
    0.40
    Copy
    0.39
    假设
    0.39
    自动化
    0.38
     ತು
    0.38
    getModel
    0.38
    Sprites
    0.37
    POSITIVE LOGITS
     Al
    0.46
     Jazeera
    0.45
     ал
    0.41
     al
    0.40
     अल
    0.40
     }{}_{\
    0.38
     roots
    0.37
     آل
    0.37
    riera
    0.37
     Pengh
    0.36
    Act Density 0.001%

    No Known Activations