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

    Neuronpedia

    INDEX
    Explanations

    -model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Runnable
    -0.07
    _STA
    -0.06
     исп
    -0.06
    klär
    -0.06
     theatrical
    -0.06
     tenía
    -0.06
    eks
    -0.06
    Retail
    -0.06
     بغ
    -0.06
     उद
    -0.06
    POSITIVE LOGITS
     disruptions
    0.07
     saya
    0.07
    ghost
    0.07
     زندگی
    0.07
     quả
    0.07
    	ch
    0.07
     结
    0.06
     bothering
    0.06
     dạng
    0.06
    pectrum
    0.06
    Act Density 0.005%

    No Known Activations