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

    Neuronpedia

    INDEX
    Explanations

    neural interface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bbb
    0.38
     compone
    0.37
     ure
    0.37
     vect
    0.37
    業
    0.36
    Css
    0.36
     Venez
    0.36
     onstage
    0.36
    VertexBuffer
    0.36
     BAB
    0.35
    POSITIVE LOGITS
    나요
    0.41
     দক্ষ
    0.40
    liv
    0.40
    ogens
    0.37
    pgsql
    0.37
    tau
    0.37
     decrypted
    0.37
    ственного
    0.36
    ulitan
    0.36
    ♒
    0.36
    Act Density 0.004%

    No Known Activations