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

    Neuronpedia

    INDEX
    Explanations

    even different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    achio
    0.42
    ře
    0.40
    hte
    0.38
    še
    0.37
     left
    0.36
    瓄
    0.35
    ari
    0.35
    ണ്ണി
    0.35
    れた
    0.35
    ise
    0.34
    POSITIVE LOGITS
    甚至
    1.66
    甚至是
    1.57
     voire
    1.54
     bahkan
    1.39
    乃至
    1.38
     thậm
    1.28
     hatta
    1.28
     এমনকি
    1.20
     Bahkan
    1.12
     وحتى
    1.11
    Act Density 0.228%

    No Known Activations