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

    Neuronpedia

    INDEX
    Explanations

    Mixed language/code fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    technik
    -0.08
    owan
    -0.07
    চ্চ
    -0.07
     Ox
    -0.07
     Forestry
    -0.07
     Bios
    -0.07
    ťaž
    -0.07
    ��
    -0.07
    మైన
    -0.07
    Ox
    -0.07
    POSITIVE LOGITS
     eql
    0.08
     tablas
    0.08
     отношение
    0.08
     bec
    0.08
    �
    0.07
     обязатель
    0.07
     önem
    0.07
     rez
    0.07
     نق
    0.07
     dây
    0.07
    Act Density 0.455%

    No Known Activations