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

    Neuronpedia

    INDEX
    Explanations

    Python Flask web development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sb
    0.54
    Ws
    0.54
    iados
    0.53
    er
    0.52
    owano
    0.52
    SPs
    0.52
    ያዎች
    0.52
     призна
    0.51
    ownic
    0.51
    ows
    0.51
    POSITIVE LOGITS
     स्वातंत्र्य
    0.49
    ន្តែ
    0.49
     tween
    0.46
    郗
    0.46
    走进
    0.45
    是对
    0.45
     দুনি
    0.44
    你好
    0.44
     khawatir
    0.44
     autistic
    0.44
    Act Density 0.001%

    No Known Activations