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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thinkable
    -0.08
     engulf
    -0.07
     מדוע
    -0.07
    יכון
    -0.07
     resolutions
    -0.07
    紧急
    -0.07
    .EventHandler
    -0.07
    .paging
    -0.07
    koneksi
    -0.06
     Andres
    -0.06
    POSITIVE LOGITS
    >An
    0.07
    Implement
    0.07
     cached
    0.07
    .Set
    0.07
     Fix
    0.07
     authority
    0.07
    fad
    0.07
     vant
    0.07
     cat
    0.07
    Analysis
    0.07
    Act Density 0.002%

    No Known Activations