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

    Neuronpedia

    INDEX
    Explanations

    list item headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    此同时
    0.35
    ેચ્છ
    0.33
    Ссы
    0.32
    考えると
    0.32
     diesem
    0.31
     sinnv
    0.31
    दिग्ध
    0.31
     thisobject
    0.31
     বুঝিতে
    0.31
    ஞ்சம்
    0.30
    POSITIVE LOGITS
    m
    0.36
     biological
    0.34
    ра
    0.34
    an
    0.34
     stools
    0.33
    ल
    0.32
    water
    0.32
     nations
    0.32
     components
    0.32
     motorcycles
    0.32
    Act Density 0.120%

    No Known Activations