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

    Neuronpedia

    INDEX
    Explanations

    fields and geometry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    শব
    0.41
    嘉宾
    0.41
     फॉलोइंग
    0.39
     التالية
    0.39
    扬
    0.38
     التالي
    0.38
    磬
    0.38
    ശാ
    0.37
     arrondies
    0.37
     বিক্রয়
    0.37
    POSITIVE LOGITS
    filesystem
    0.42
     realm
    0.40
     environments
    0.40
    地面
    0.38
    ड्या
    0.38
     all
    0.38
     ሲ
    0.38
     realms
    0.37
     sphere
    0.37
     ө
    0.37
    Act Density 0.000%

    No Known Activations