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

    Neuronpedia

    INDEX
    Explanations

    git

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tension
    -0.08
     excerpt
    -0.06
    dfunding
    -0.06
     implying
    -0.06
    �u
    -0.06
    Today
    -0.06
    ,”
    -0.06
     undermines
    -0.06
     intertw
    -0.06
    ("?
    -0.06
    POSITIVE LOGITS
     çalışan
    0.07
     Genetics
    0.07
     منط
    0.06
     počet
    0.06
     TEntity
    0.06
     marty
    0.06
     GX
    0.06
     enamel
    0.06
    ела
    0.06
     Roe
    0.06
    Act Density 0.003%

    No Known Activations