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

    Neuronpedia

    INDEX
    Explanations

    it like this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ඒවා
    0.91
     அவற்றில்
    0.88
     వాటి
    0.77
     সেগুলো
    0.76
     அவற்றை
    0.75
     ಅವು
    0.73
     அவை
    0.71
     उसमें
    0.71
     அவற்ற
    0.70
    oretically
    0.68
    POSITIVE LOGITS
     this
    6.80
    this
    6.55
     هذا
    5.97
     этого
    5.69
     questo
    5.67
     questa
    5.56
     acest
    5.36
     этом
    5.35
    This
    5.29
     этой
    5.27
    Act Density 5.221%

    No Known Activations