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

    Neuronpedia

    INDEX
    Explanations

    Military context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Accounting
    -0.07
     Bernie
    -0.07
    anye
    -0.07
     Video
    -0.07
    样子
    -0.07
     Engineers
    -0.07
     airplanes
    -0.06
    ipped
    -0.06
     concession
    -0.06
     Temperature
    -0.06
    POSITIVE LOGITS
    �
    0.07
     NotSupportedException
    0.07
     başarılı
    0.06
    .Prot
    0.06
     πολι
    0.06
    .effect
    0.06
    Live
    0.06
    ��
    0.06
    بع
    0.06
    Resistance
    0.06
    Act Density 0.014%

    No Known Activations