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

    Neuronpedia

    INDEX
    Explanations

    rape and women

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UIControl
    -0.07
     CGRect
    -0.06
     powerful
    -0.06
     Montreal
    -0.06
     °
    -0.06
     revolves
    -0.06
     NX
    -0.06
    _expect
    -0.06
    нице
    -0.06
     провер
    -0.06
    POSITIVE LOGITS
     Investments
    0.07
     Credit
    0.07
    Additional
    0.06
    िनक
    0.06
    .General
    0.06
     adversaries
    0.06
    ================================
    0.06
     indices
    0.06
     Secretary
    0.06
     secretary
    0.06
    Act Density 0.211%

    No Known Activations