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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ret
    -0.08
     thereby
    -0.07
     município
    -0.07
    据悉
    -0.07
     InputDecoration
    -0.07
    总公司
    -0.07
     وأشار
    -0.06
     cheg
    -0.06
    𝕁
    -0.06
     إلا
    -0.06
    POSITIVE LOGITS
     playlists
    0.08
    Study
    0.07
     trope
    0.07
    uien
    0.07
     CMP
    0.07
    enchmark
    0.07
    ressed
    0.07
    asurement
    0.07
    perform
    0.07
     appl
    0.06
    Act Density 0.001%

    No Known Activations