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

    Neuronpedia

    INDEX
    Explanations

    reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্ডিং
    0.42
     lose
    0.40
    见面
    0.39
     बहन
    0.39
     gubit
    0.39
     selecionar
    0.38
    prnewswire
    0.38
    नेक
    0.38
     diseñar
    0.37
    連
    0.37
    POSITIVE LOGITS
     характеристи
    0.42
     descript
    0.41
    Reference
    0.39
     Reference
    0.38
     soi
    0.37
     参考
    0.37
     reference
    0.36
    そ
    0.36
     champion
    0.36
     hasty
    0.36
    Act Density 0.001%

    No Known Activations