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

    Neuronpedia

    INDEX
    Explanations

    grades

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     QtAws
    -0.09
    乃
    -0.07
     yardım
    -0.07
     محمود
    -0.07
    .connected
    -0.07
     Mosque
    -0.07
    _vp
    -0.07
    寁
    -0.07
     Doctor
    -0.06
     Araştırma
    -0.06
    POSITIVE LOGITS
     Pent
    0.07
    式的
    0.07
    	PORT
    0.07
    _components
    0.07
    missible
    0.06
    .stem
    0.06
    params
    0.06
    值得一提
    0.06
    *=
    0.06
    incip
    0.06
    Act Density 0.026%

    No Known Activations