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

    Neuronpedia

    INDEX
    Explanations

    War on drugs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Descriptor
    -0.09
     সাধ
    -0.08
     তিন
    -0.08
    _descriptor
    -0.08
    urdy
    -0.08
    descriptor
    -0.08
     पति
    -0.08
     vorhand
    -0.08
     আদাল
    -0.08
    Manipulator
    -0.08
    POSITIVE LOGITS
     disproportionately
    0.09
     tariffs
    0.08
    .As
    0.08
     disproportion
    0.08
     उत
    0.08
     unnecessarily
    0.08
     Bush
    0.07
    Bush
    0.07
     greedy
    0.07
     quotas
    0.07
    Act Density 0.014%

    No Known Activations