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

    Neuronpedia

    INDEX
    Explanations

    date

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    據
    -0.07
     Advertisement
    -0.06
    (nil
    -0.06
    namespace
    -0.06
     Encounter
    -0.06
    uur
    -0.06
    ijk
    -0.06
    ací
    -0.06
     очень
    -0.06
    opl
    -0.06
    POSITIVE LOGITS
    obre
    0.07
    snap
    0.06
     Pelosi
    0.06
    outfile
    0.06
    aption
    0.06
    nit
    0.06
     firepower
    0.06
     muslim
    0.06
    .getConnection
    0.06
    mam
    0.06
    Act Density 0.012%

    No Known Activations