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

    Neuronpedia

    INDEX
    Explanations

    Social class

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pert
    -0.08
     Also
    -0.07
     bless
    -0.07
     wrench
    -0.07
     longer
    -0.07
    arr
    -0.07
    DEM
    -0.07
    水务
    -0.07
     brass
    -0.07
     Inspection
    -0.07
    POSITIVE LOGITS
    .Level
    0.07
    .arraycopy
    0.07
    _soup
    0.07
    _merge
    0.07
    /operators
    0.07
    proposal
    0.07
    مشاه
    0.07
    (entry
    0.07
    elite
    0.07
    ])[
    0.07
    Act Density 0.132%

    No Known Activations