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

    Neuronpedia

    INDEX
    Explanations

    story plots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    repid
    -0.06
    reating
    -0.06
     powers
    -0.06
    hard
    -0.06
    Needs
    -0.06
    procs
    -0.06
    needs
    -0.06
     Rights
    -0.06
     obligated
    -0.06
    preferred
    -0.06
    POSITIVE LOGITS
     hâlâ
    0.07
    것
    0.07
     PVOID
    0.07
     Laos
    0.07
     где
    0.07
    させ
    0.06
    ?>">
    0.06
    ildiği
    0.06
     ‫
    0.06
    lıyor
    0.06
    Act Density 0.169%

    No Known Activations