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

    Neuronpedia

    INDEX
    Explanations

    Istanbul, Stuart, NRI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    亚太
    0.54
     लिये
    0.54
    不对
    0.52
     Copa
    0.51
     द
    0.50
     Instituto
    0.50
    म
    0.49
     Ettha
    0.49
     Config
    0.49
     उत्तर
    0.49
    POSITIVE LOGITS
     setzen
    0.46
    嘩
    0.44
     helpen
    0.43
     barber
    0.43
    ﻷ
    0.42
     masa
    0.41
     barrier
    0.41
    tarea
    0.41
    عد
    0.41
    েইলি
    0.41
    Act Density 0.000%

    No Known Activations