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

    Neuronpedia

    INDEX
    Explanations

    women

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pent
    -0.06
    öyle
    -0.06
     можливість
    -0.06
    	NS
    -0.06
     PLAN
    -0.06
     LU
    -0.06
    .btn
    -0.06
     tourists
    -0.06
     carniv
    -0.06
    _don
    -0.06
    POSITIVE LOGITS
     serialized
    0.07
     intricate
    0.07
    \core
    0.07
    AsString
    0.06
     drain
    0.06
    Magnitude
    0.06
    -semibold
    0.06
     unfore
    0.06
    conte
    0.06
    .forms
    0.06
    Act Density 0.013%

    No Known Activations