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

    Neuronpedia

    INDEX
    Explanations

    Serve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rien
    -0.07
    -0.06
     Lotus
    -0.06
    igest
    -0.06
    ्पष
    -0.06
     اصفه
    -0.06
    体
    -0.06
    -head
    -0.06
    Markup
    -0.06
     kém
    -0.06
    POSITIVE LOGITS
     vic
    0.07
    /weather
    0.07
     بخش
    0.07
    #SBATCH
    0.06
     broadband
    0.06
     LIS
    0.06
    “↵↵
    0.06
    typeorm
    0.06
    _chars
    0.06
    ader
    0.06
    Act Density 0.006%

    No Known Activations