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

    Neuronpedia

    INDEX
    Explanations

    RE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emale
    -0.07
    Slave
    -0.07
    mall
    -0.06
    oley
    -0.06
    frog
    -0.06
    CCA
    -0.06
    Dog
    -0.06
    female
    -0.06
    ,\
    -0.06
    ↵↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
     aeros
    0.07
     invention
    0.07
     Elev
    0.06
     behaviour
    0.06
     allowable
    0.06
     behavior
    0.06
     ApplicationDbContext
    0.06
     existence
    0.06
     PIO
    0.06
     AREA
    0.06
    Act Density 0.179%

    No Known Activations