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

    Neuronpedia

    INDEX
    Explanations

    errors in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -info
    -0.07
    惠
    -0.07
    elig
    -0.07
     headers
    -0.06
    txt
    -0.06
    ansas
    -0.06
    mue
    -0.06
    (main
    -0.06
    翔
    -0.06
    ι
    -0.06
    POSITIVE LOGITS
     SVC
    0.06
    NK
    0.06
     xyz
    0.06
     води
    0.06
    vědom
    0.06
     jejich
    0.06
     kent
    0.06
     листоп
    0.06
     нал
    0.06
     TEX
    0.06
    Act Density 0.035%

    No Known Activations