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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Colombia
    -0.07
     drv
    -0.07
     Simulation
    -0.07
    ób
    -0.07
     ques
    -0.07
     (_,
    -0.07
     titt
    -0.07
    生命周期
    -0.07
     Mexico
    -0.07
    模拟
    -0.06
    POSITIVE LOGITS
    stood
    0.09
     memang
    0.08
     ipp
    0.08
     정말
    0.08
     gerçekten
    0.08
     lohnt
    0.08
    łoż
    0.07
     underestimated
    0.07
    strand
    0.07
     Caravan
    0.07
    Act Density 0.092%

    No Known Activations