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

    Neuronpedia

    INDEX
    Explanations

    locations and subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wrapper
    0.39
    Tar
    0.38
     musicales
    0.38
     morale
    0.37
    Vine
    0.37
    Glare
    0.37
    iminaries
    0.37
    オ
    0.37
     OA
    0.36
     وین
    0.36
    POSITIVE LOGITS
     گئے
    0.41
     вектор
    0.39
     splike
    0.38
     dafür
    0.38
    cadherin
    0.38
    钚
    0.37
    ப்பதற்காக
    0.36
     সম্ভব
    0.35
    ிருக்கிறார்
    0.35
     haben
    0.35
    Act Density 0.000%

    No Known Activations