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

    Neuronpedia

    INDEX
    Explanations

    manpower

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spikes
    -0.08
     nurs
    -0.07
     reverse
    -0.07
     Seg
    -0.07
    ��
    -0.06
     Waters
    -0.06
     segu
    -0.06
     Superior
    -0.06
    ,temp
    -0.06
     Pretty
    -0.06
    POSITIVE LOGITS
    Appointment
    0.08
    CHAPTER
    0.08
    olvable
    0.07
     fright
    0.07
     workforce
    0.07
    :SetText
    0.07
     onDataChange
    0.06
    �
    0.06
    مارات
    0.06
    igure
    0.06
    Act Density 0.033%

    No Known Activations