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

    Neuronpedia

    INDEX
    Explanations

    prosecution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     유
    -0.07
    alog
    -0.07
     twilight
    -0.07
     �
    -0.07
     leaning
    -0.06
     Alpine
    -0.06
     günlük
    -0.06
    輪
    -0.06
    奇
    -0.06
    7
    -0.06
    POSITIVE LOGITS
     prosecutors
    0.08
     prosecuted
    0.07
    负责
    0.07
     qb
    0.07
    populate
    0.07
    招聘
    0.07
     prosecutions
    0.07
     implementations
    0.07
    Accuracy
    0.07
    Publish
    0.06
    Act Density 0.005%

    No Known Activations