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

    Neuronpedia

    INDEX
    Explanations

    agent manager

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Projects
    -0.07
     sour
    -0.06
    خت
    -0.06
     rad
    -0.06
     змі
    -0.06
     قادر
    -0.06
    赛
    -0.06
    accur
    -0.06
    озем
    -0.06
     getopt
    -0.06
    POSITIVE LOGITS
    Px
    0.07
    急
    0.06
    両
    0.06
     detectives
    0.06
    уз
    0.06
     cart
    0.06
    ồn
    0.06
     Maintenance
    0.06
    �
    0.06
    pped
    0.06
    Act Density 0.009%

    No Known Activations