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

    Neuronpedia

    INDEX
    Explanations

    names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Solidity
    0.24
     Apica
    0.23
    .${
    0.23
     powering
    0.23
    EndPoint
    0.22
     <--
    0.22
    0.22
     initialized
    0.22
     ->
    0.22
     Koj
    0.22
    POSITIVE LOGITS
    ম্ত
    0.27
    ੱ
    0.24
    homme
    0.21
     vậy
    0.20
    ក
    0.20
    gaard
    0.20
     mewn
    0.19
     chasse
    0.19
    PhysRev
    0.19
    ませんでした
    0.19
    Act Density 0.128%

    No Known Activations