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

    Neuronpedia

    INDEX
    Explanations

    prisons and incarceration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     screwed
    -0.07
    kou
    -0.07
    434
    -0.07
    EqualityComparer
    -0.07
     convict
    -0.06
    439
    -0.06
    iales
    -0.06
    اشین
    -0.06
    'nin
    -0.06
    Govern
    -0.06
    POSITIVE LOGITS
    (be
    0.07
    -company
    0.06
     설명
    0.06
    .solve
    0.06
     в
    0.06
     getNext
    0.06
    нения
    0.06
     xml
    0.06
     conqu
    0.06
     batch
    0.06
    Act Density 0.048%

    No Known Activations